Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning (sign in to use)

Saturday 31 January

Machine Learning

PyGALAX: An Open-Source Python Toolkit for Advanced Explainable Geospatial Machine Learning

PyGALAX is a Python package for geospatial analysis that integrates automated machine learning (AutoML) and explainable artificial intelligence (XAI) techniques to analyze spatial heterogeneity in both regression and classification tasks. It automatically selects and optimizes machine learning models for different geographic locations and contexts while maintaining interpretability through SHAP (SHapley Additive exPlanations) analysis. PyGALAX builds upon and improves the GALAX framework (Geospatial Analysis Leveraging AutoML and eXplainable AI), which has proven to outperform traditional geographically weighted regression (GWR) methods. Critical enhancements in PyGALAX from the original GALAX framework include automatic bandwidth selection and flexible kernel function selection, providing greater flexibility and robustness for spatial modeling across diverse datasets and research questions. PyGALAX not only inherits all the functionalities of the original GALAX framework but also packages them into an accessible, reproducible, and easily deployable Python toolkit while providing additional options for spatial modeling. It effectively addresses spatial non-stationarity and generates transparent insights into complex spatial relationships at both global and local scales, making advanced geospatial machine learning methods accessible to researchers and practitioners in geography, urban planning, environmental science, and related fields.
Read the full abstract

All authors Pingping Wang, Yihong Yuan, Lingcheng Li, Yongmei Lu

Machine Learning

Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing

Large language models often hallucinate with high confidence on "random facts" that lack inferable patterns. We formalize the memorization of such facts as a membership testing problem, unifying the discrete error metrics of Bloom filters with the continuous log-loss of LLMs. By analyzing this problem in the regime where facts are sparse in the universe of plausible claims, we establish a rate-distortion theorem: the optimal memory efficiency is characterized by the minimum KL divergence between score distributions on facts and non-facts. This theoretical framework provides a distinctive explanation for hallucination under an idealized setting: even with optimal training, perfect data, and a simplified “closed world” setting, the information-theoretically optimal strategy under limited capacity is not to abstain or forget, but to assign high confidence to some non-facts, resulting in hallucination. We validate this theory empirically on both synthetic and real-world data, showing that hallucinations persist as a natural consequence of lossy compression. The same theorem recovers and sharpens classical space lower bounds for Bloom-type filters, pinning down an additive constant left open for two-sided filters.
Read the full abstract

Machine Learning

Domain-Adaptive and Scalable Dense Retrieval for Content-Based Recommendation

E-commerce recommendation and search commonly rely on sparse keyword matching (e.g., BM25), which breaks down under vocabulary mismatch when user intent has limited lexical overlap with product metadata. We cast content-based recommendation as recommendation-as-retrieval: given a natural-language intent signal (a query or review), retrieve the top-K most relevant items from a large catalog via semantic similarity. We present a scalable dense retrieval system based on a two-tower bi-encoder, fine-tuned on the Amazon Reviews 2023 (Fashion) subset using supervised contrastive learning with Multiple Negatives Ranking Loss. We construct training pairs from review text (as a query proxy) and item metadata (as the positive document) and fine-tune on 50,000 sampled interactions with a maximum sequence length of 500 tokens. For efficient serving, we combine FAISS HNSW indexing with an ONNX Runtime inference pipeline using INT8 dynamic quantization. On a review-to-title benchmark over 826,402 catalog items, our approach improves Recall@10 from 0.26 (BM25) to 0.66, while meeting practical latency and model-size constraints: 6.1 ms median CPU inference latency (batch size 1) and a 4x reduction in model size. Overall, we provide an end-to-end, reproducible blueprint for taking domain-adapted dense retrieval from offline training to CPU-efficient serving at catalog scale.
Read the full abstract

2602.00899 · 31 Jan · 13 pages, 4 figures. Semantic dense retrieval for content-based recommendation on Amazon Reviews 2023 (Category - Fashion). Dataset statistics: 2.0M users; 825.9K items; 2.5M ratings; 94.9M review tokens; 510.5M metadata tokens. Timespan: May 1996 to September 2023. Metadata includes: user reviews (ratings, text, helpfulness votes, etc.); item metadata (descriptions, price, raw images, etc.)

Machine Learning

GAPNet: Plug-in Jointly Learning Task-Specific Graph for Dynamic Stock Relation

The advent of the web has led to a paradigm shift in the financial relations, with the real-time dissemination of news, social discourse, and financial filings contributing significantly to the reshaping of financial forecasting. The existing methods rely on establishing relations a priori, i.e. predefining graphs to capture inter-stock relationships. However, the stock-related web signals are characterised by high levels of noise, asynchrony, and challenging to obtain, resulting in poor generalisability and non-alignment between the predefined graphs and the downstream tasks. To address this, we propose GAPNet, a Graph Adaptation Plug-in Network that jointly learns task-specific topology and representations in an end-to-end manner. GAPNet attaches to existing pairwise graph or hypergraph backbone models, enabling the dynamic adaptation and rewiring of edge topologies via two complementary components: a Spatial Perception Layer that captures short-term co-movements across assets, and a Temporal Perception Layer that maintains long-term dependency under distribution shift. Across two real-world stock datasets, GAPNet has been shown to consistently enhance the profitability and stability in comparision to the state-of-the-art models, yielding annualised cumulative returns of up to 0.47 for RT-GCN and 0.63 for CI-STHPAN, with peak Sharpe Ratio of 2.20 and 2.12 respectively. The plug-and-play design of GAPNet ensures its broad applicability to diverse GNN-based architectures. Our results underscore that jointly learning graph structures and representations is essential for task-specific relational modeling.
Read the full abstract

All authors Yingjie Niu, Lanxin Lu, Changhong Jin, Ruihai Dong

Machine Learning · Cross-listed from cs.CL

EffGen: Enabling Small Language Models as Capable Autonomous Agents

Most existing language model agentic systems today are built and optimized for large language models (e.g., GPT, Claude, Gemini) via API calls; while powerful, this approach faces several limitations including high token costs and privacy concerns for sensitive applications. We introduce EffGen, an open-source agentic framework optimized for small language models (SLMs) that enables effective, efficient, and secure local deployment. EffGen makes four major contributions: (1) Enhanced tool-calling with prompt optimization that compresses input prompts by up to 70-80% (and 57% on average across our benchmarks) while preserving task semantics, (2) Intelligent task decomposition that breaks complex queries into parallel or sequential subtasks based on dependencies, (3) Complexity-based routing using five factors to make smart pre-execution decisions, and (4) Unified memory system combining short-term, long-term, and vector-based storage. Additionally, EffGen unifies multiple agent protocols (MCP, A2A, ACP) for cross-protocol communication. Results on 13 benchmarks show EffGen outperforms LangChain, AutoGen, and Smolagents with higher success rates, faster execution, and lower memory. Our results reveal that prompt optimization and complexity routing have complementary scaling behavior: optimization benefits SLMs more (11.2% gain at 1.5B vs 2.4% at 32B), while routing benefits large models more (3.6% at 1.5B vs 7.9% at 32B), providing consistent gains across all scales when combined. EffGen is released under the Apache 2.0 License, ensuring broad accessibility for research and commercial use, with the code available at https://github.com/ctrl-gaurav/effGen, the Python package at https://pypi.org/project/effgen/ (pip install effgen), and the project website and documentation at https://effgen.org/ and https://docs.effgen.org/.
Read the full abstract

All authors Gaurav Srivastava, Aafiya Hussain, Chi Wang, Yingyan Celine Lin, Xuan Wang

Machine Learning · Cross-listed from cs.RO

RoDiF: Robust Direct Fine-Tuning of Diffusion Policies with Corrupted Human Feedback

Diffusion policies are a powerful paradigm for robotic control, but fine-tuning them with human preferences is fundamentally challenged by the multi-step structure of the denoising process. To overcome this, we introduce a Unified Markov Decision Process (MDP) formulation that coherently integrates the diffusion denoising chain with environmental dynamics, enabling reward-free Direct Preference Optimization (DPO) for diffusion policies. Building on this formulation, we propose RoDiF (Robust Direct Fine-Tuning), a method that explicitly addresses corrupted human preferences. RoDiF reinterprets the DPO objective through a geometric hypothesis-cutting perspective and employs a conservative cutting strategy to achieve robustness without assuming any specific noise distribution. Extensive experiments on long-horizon manipulation tasks show that RoDiF consistently outperforms state-of-the-art baselines, effectively steering pretrained diffusion policies of diverse architectures to human-preferred modes, while maintaining strong performance even under 30% corrupted preference labels.
Read the full abstract

Machine Learning

Reliability-Aware Determinantal Point Processes for Robust Informative Data Selection in Large Language Models

Informative data selection is a key requirement for large language models (LLMs) to minimize the amount of data required for fine-tuning, network distillation, and token pruning, enabling fast and efficient deployment, especially under computational and communication constraints. Traditional subset selection methods, including those based on Determinantal Point Processes (DPP), focus on maximizing diversity but assume that selected data batches are always available error-free. This presumption prohibits their use under partial storage outage, imperfect communication, and stochastic access failures. Furthermore, we show that the original formulation collapses under such conditions. To address this gap, we introduce ProbDPP, a novel reliability-aware implementation of k-DPP that accounts for probabilistic data access by recasting the objective function with a regularization term that remains well-posed and decomposes into a geometric diversity term and unreliability cost. The resulting objective facilitates robust selection of diverse data batches under uncertainty. Furthermore, we frame this reliability-aware diversity maximization as a combinatorial semi-bandit problem and propose a UCB-style algorithm to efficiently learn the unknown reliability online. Theoretical analysis provides regret bounds for the proposed approach, ensuring performance guarantees.
Read the full abstract

Machine Learning

Test-time Generalization for Physics through Neural Operator Splitting

Neural operators have shown promise in learning solution maps of partial differential equations (PDEs), but they often struggle to generalize when test inputs lie outside the training distribution, such as novel initial conditions, unseen PDE coefficients or unseen physics. Prior works address this limitation with large-scale multiple physics pretraining followed by fine-tuning, but this still require examples from the new dynamics, falling short of true zero-shot generalization. In this work, we propose a method to enhance generalization at test time, i.e., without modifying pretrained weights. Building on DISCO, which provides a dictionary of neural operators trained across different dynamics, we introduce a neural operator splitting strategy that, at test time, searches over compositions of training operators to approximate unseen dynamics.On challenging out-of-distribution tasks including parameter extrapolation and novel combinations of physics phenomena, our approach achieves state-of-the-art zero-shot generalization results, while being able to recover the underlying PDE parameters. These results underscore test-time computation as a key avenue for building flexible, compositional, and generalizable neural operators.
Read the full abstract

All authors Louis Serrano, Jiequn Han, Edouard Oyallon, Shirley Ho, Rudy Morel

Machine Learning

Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs

Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their integration with Mixture-of-Experts (MoE) architectures is constrained by an expert explosion: as the number of tokens generated in parallel increases, the number of distinct experts activated grows nearly linearly. This results in substantial memory traffic that pushes inference into a memory-bound regime, negating the efficiency gains of both MoE and parallel decoding. To address this challenge, we propose Dynamic Expert Sharing (DES), a novel technique that shifts MoE optimization from token-centric pruning and conventional expert skipping methods to sequence-level coreset selection. To maximize expert reuse, DES identifies a compact, high-utility set of experts to satisfy the requirements of an entire parallel decoding block. We introduce two innovative selection strategies: (1) Intra-Sequence Sharing (DES-Seq), which adapts optimal allocation to the sequence level, and (2) Saliency-Aware Voting (DES-Vote), a novel mechanism that allows tokens to collectively elect a coreset based on aggregated router weights. Extensive experiments on MoE dLLMs demonstrate that DES reduces unique expert activations by over 55% and latency by up to 38%, while retaining 99% of vanilla accuracy, effectively decoupling memory overhead from the degree of parallelism.
Read the full abstract

All authors Hao Mark Chen, Zhiwen Mo, Royson Lee, Qianzhou Wang, Da Li, Shell Xu Hu, Wayne Luk, Timothy Hospedales, Hongxiang Fan

Machine Learning · Cross-listed from quant-ph

Sublinear Time Quantum Algorithm for Attention Approximation

Given the query, key and value matrices $Q, K, V\in \mathbb{R}^{n\times d}$, the attention module is defined as $\mathrm{Att}(Q, K, V)=D^{-1}AV$ where $A=\exp(QK^\top/\sqrt{d})$ with $\exp(\cdot)$ applied entrywise, $D=\mathrm{diag}(A{\bf 1}_n)$. The attention module is the backbone of modern transformers and large language models, but explicitly forming the softmax matrix $D^{-1}A$ incurs $\Omega(n^2)$ time, motivating numerous approximation schemes that reduce runtime to $\widetilde O(nd)$ via sparsity or low-rank factorization. We propose a quantum data structure that approximates any row of $\mathrm{Att}(Q, K, V)$ using only row queries to $Q, K, V$. Our algorithm preprocesses these matrices in $\widetilde{O}\left( \epsilon^{-1} n^{0.5} \left( s_\lambda^{2.5} + s_\lambda^{1.5} d + \alpha^{0.5} d \right) \right)$ time, where $\epsilon$ is the target accuracy, $s_\lambda$ is the $\lambda$-statistical dimension of the exponential kernel defined by $Q$ and $K$, and $\alpha$ measures the row distortion of $V$ that is at most $d/{\rm srank}(V)$, the stable rank of $V$. Each row query can be answered in $\widetilde{O}(s_\lambda^2 + s_\lambda d)$ time. To our knowledge, this is the first quantum data structure that approximates rows of the attention matrix in sublinear time with respect to $n$. Our approach relies on a quantum Nyström approximation of the exponential kernel, quantum multivariate mean estimation for computing $D$, and quantum leverage score sampling for the multiplication with $V$.
Read the full abstract

All authors Zhao Song, Jianfei Xue, Jiahao Zhang, Lichen Zhang

Machine Learning

Learning Heat-based Equations in Self-similar variables

We study solution learning for heat-based equations in self-similar variables (SSV). We develop an SSV training framework compatible with standard neural-operator training. We instantiate this framework on the two-dimensional incompressible Navier-Stokes equations and the one-dimensional viscous Burgers equation, and perform controlled comparisons between models trained in physical coordinates and in the corresponding self-similar coordinates using two simple fully connected architectures (standard multilayer perceptrons and a factorized fully connected network). Across both systems and both architectures, SSV-trained networks consistently deliver substantially more accurate and stable extrapolation beyond the training window and better capture qualitative long-time trends. These results suggest that self-similar coordinates provide a mathematically motivated inductive bias for learning the long-time dynamics of heat-based equations.
Read the full abstract

Machine Learning

Improving Flow Matching by Aligning Flow Divergence

Conditional flow matching (CFM) stands out as an efficient, simulation-free approach for training flow-based generative models, achieving remarkable performance for data generation. However, CFM is insufficient to ensure accuracy in learning probability paths. In this paper, we introduce a new partial differential equation characterization for the error between the learned and exact probability paths, along with its solution. We show that the total variation gap between the two probability paths is bounded above by a combination of the CFM loss and an associated divergence loss. This theoretical insight leads to the design of a new objective function that simultaneously matches the flow and its divergence. Our new approach improves the performance of the flow-based generative model by a noticeable margin without sacrificing generation efficiency. We showcase the advantages of this enhanced training approach over CFM on several important benchmark tasks, including generative modeling for dynamical systems, DNA sequences, and videos. Code is available at \href{https://github.com/Utah-Math-Data-Science/Flow_Div_Matching}{Utah-Math-Data-Science}.
Read the full abstract

All authors Yuhao Huang, Taos Transue, Shih-Hsin Wang, William Feldman, Hong Zhang, Bao Wang

Machine Learning

Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs

Graph neural networks (GNNs) have emerged as powerful tools for learning protein structures by capturing spatial relationships at the residue level. However, existing GNN-based methods often face challenges in learning multiscale representations and modeling long-range dependencies efficiently. In this work, we propose an efficient multiscale graph-based learning framework tailored to proteins. Our proposed framework contains two crucial components: (1) It constructs a hierarchical graph representation comprising a collection of fine-grained subgraphs, each corresponding to a secondary structure motif (e.g., $\alpha$-helices, $\beta$-strands, loops), and a single coarse-grained graph that connects these motifs based on their spatial arrangement and relative orientation. (2) It employs two GNNs for feature learning: the first operates within individual secondary motifs to capture local interactions, and the second models higher-level structural relationships across motifs. Our modular framework allows a flexible choice of GNN in each stage. Theoretically, we show that our hierarchical framework preserves the desired maximal expressiveness, ensuring no loss of critical structural information. Empirically, we demonstrate that integrating baseline GNNs into our multiscale framework remarkably improves prediction accuracy and reduces computational cost across various benchmarks.
Read the full abstract

All authors Shih-Hsin Wang, Yuhao Huang, Taos Transue, Justin Baker, Jonathan Forstater, Thomas Strohmer, Bao Wang

Machine Learning · Cross-listed from cs.AI

Multi-Head Attention Is a Multi-Player Game

Modern transformer attention is internally multi-agent – heads compete and coordinate – yet we train it as if it were a monolithic optimizer. We formalize this gap: cross-entropy training induces an implicit potential game among heads, and gradient descent converges to Nash equilibria with potentially unbounded inefficiency due to unpriced externalities (redundancy, correlated errors). Our main result bounds the Price of Anarchy by $\Gamma(G)$, the off-diagonal mass of a head interaction matrix capturing weight and gradient coupling. Under mild smoothness assumptions, we prove that both excess hallucination probability and excess head redundancy scale with PoA, unifying two distinct failure modes into a single mechanism. The bound is prescriptive: regularization that reduces $\Gamma(G)$ provably tightens PoA. We instantiate this as GAME-LoRA, combining Barlow Twins decorrelation with log-determinant coordination pressure. Experiments validate the theory: $\Gamma(G)$ predicts hallucination ($p{<}0.05$), emergent coalitions exhibit selective coordination, and GAME-LoRA achieves up to 18% hallucination reduction (8% average) with no knowledge degradation – a Pareto improvement inaccessible to methods ignoring the game structure.
Read the full abstract

Machine Learning

Investigating the Robustness of Subtask Distillation under Spurious Correlation

Subtask distillation is an emerging paradigm in which compact, specialized models are extracted from large, general-purpose 'foundation models' for deployment in environments with limited resources or in standalone computer systems. Although distillation uses a teacher model, it still relies on a dataset that is often limited in size and may lack representativeness or exhibit spurious correlations. In this paper, we evaluate established distillation methods, as well as the recent SubDistill method, when using data with spurious correlations for distillation. As the strength of the correlations increases, we observe a widening gap between advanced methods, such as SubDistill, which remain fairly robust, and some baseline methods, which degrade to near-random performance. Overall, our study underscores the challenges of knowledge distillation when applied to imperfect, real-world datasets, particularly those with spurious correlations.
Read the full abstract

Machine Learning

RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation

Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this issue by introducing RMFlow, an efficient multimodal generative model that integrates a coarse 1-NFE MeanFlow transport with a subsequent tailored noise-injection refinement step. RMFlow approximates the average velocity of the flow path using a neural network trained with a new loss function that balances minimizing the Wasserstein distance between probability paths and maximizing sample likelihood. RMFlow achieves near state-of-the-art results on text-to-image, context-to-molecule, and time-series generation using only 1-NFE, at a computational cost comparable to the baseline MeanFlows.
Read the full abstract

All authors Yuhao Huang, Shih-Hsin Wang, Andrea L. Bertozzi, Bao Wang

Machine Learning · Cross-listed from stat.ML

Multivariate Time Series Data Imputation via Distributionally Robust Regularization

Multivariate time series imputation is often compromised by mismatch between the observed and true data distributions, a bias induced by the combined effects of time-series non-stationarity and systematic missingness. Standard methods that encourage point-wise reconstruction or direct distributional alignment may overfit these biased observations. We propose the Distributionally Robust Regularized Imputer Objective (DRIO), which jointly minimizes reconstruction error and the worst-case divergence between the imputer distribution and data distributions within a Wasserstein ambiguity set. We derive a tractable upper-bound surrogate that reduces infinite-dimensional optimization over measures to adversarial search over sample trajectories, and develop an alternating learning algorithm compatible with modern deep learning backbones. Comprehensive experiments on diverse real-world datasets show that DRIO consistently provides robust imputation and suggests improved downstream forecasting under various missingness scenarios.
Read the full abstract

All authors Che-Yi Liao, Zheng Dong, Gian-Gabriel Garcia, Kamran Paynabar

Machine Learning · Cross-listed from stat.ML

Score-based Metropolis-Hastings for Fractional Langevin Algorithms

Sampling from heavy-tailed and multimodal distributions is challenging when neither the target density nor the proposal density can be evaluated, as in $\alpha$-stable Lévy-driven fractional Langevin algorithms. While the target distribution can be estimated from data via score-based or energy-based models, the $\alpha$-stable proposal density and its score are generally unavailable, rendering classical density-based Metropolis–Hastings (MH) corrections impractical. Consequently, existing fractional Langevin methods operate in an unadjusted regime and can exhibit substantial finite-time errors and poor empirical control of tail behavior. We introduce the Metropolis-Adjusted Fractional Langevin Algorithm (MAFLA), an MH-inspired, fully score-based correction mechanism. MAFLA employs designed proxies for fractional proposal score gradients under isotropic symmetric $\alpha$-stable noise and learns an acceptance function via Score Balance Matching. We empirically illustrate the strong performance of MAFLA on a series of tasks including combinatorial optimization problems where the method significantly improves finite time sampling accuracy over unadjusted fractional Langevin dynamics.
Read the full abstract

All authors Ahmed Aloui, Junyi Liao, Ali Hasan, Jose Blanchet, Vahid Tarokh

Machine Learning

A Minimum Variance Path Principle for Accurate and Stable Score-Based Density Ratio Estimation

Score-based methods are powerful across machine learning, but they face a paradox: theoretically path-independent, yet practically path-dependent. We resolve this by proving that practical training objectives differ from the ideal, ground-truth objective by a crucial, overlooked term: the path variance of the score function. We propose the MVP (**M**imum **V**ariance **P**ath) Principle to minimize this path variance. Our key contribution is deriving a closed-form expression for the variance, making optimization tractable. By parameterizing the path with a flexible Kumaraswamy Mixture Model, our method learns data-adaptive, low-variance paths without heuristic manual selection. This principled optimization of the complete objective yields more accurate and stable estimators, establishing new state-of-the-art results on challenging benchmarks and providing a general framework for optimizing score-based interpolation. Our code can be found in https://github.com/Hoemr/OpenDRE.git.
Read the full abstract

All authors Wei Chen, Jiacheng Li, Shigui Li, Zhiqi Lin, Junmei Yang, John Paisley, Delu Zeng

Machine Learning

Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization

Feature learning strength (FLS), i.e., the inverse of the effective output scaling of a model, plays a critical role in shaping the optimization dynamics of neural nets. While its impact has been extensively studied under the asymptotic regimes – both in training time and FLS – existing theory offers limited insight into how FLS affects generalization in practical settings, such as when training is stopped upon reaching a target training risk. In this work, we investigate the impact of FLS on generalization in deep networks under such practical conditions. Through empirical studies, we first uncover the emergence of an $\textit{optimal FLS}$ – neither too small nor too large – that yields substantial generalization gains. This finding runs counter to the prevailing intuition that stronger feature learning universally improves generalization. To explain this phenomenon, we develop a theoretical analysis of gradient flow dynamics in two-layer ReLU nets trained with logistic loss, where FLS is controlled via initialization scale. Our main theoretical result establishes the existence of an optimal FLS arising from a trade-off between two competing effects: An excessively large FLS induces an $\textit{over-alignment}$ phenomenon that degrades generalization, while an overly small FLS leads to $\textit{over-fitting}$.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Harmful Overfitting in Sobolev Spaces

Motivated by recent work on benign overfitting in overparameterized machine learning, we study the generalization behavior of functions in Sobolev spaces $W^{k, p}(\mathbb{R}^d)$ that perfectly fit a noisy training data set. Under assumptions of label noise and sufficient regularity in the data distribution, we show that approximately norm-minimizing interpolators, which are canonical solutions selected by smoothness bias, exhibit harmful overfitting: even as the training sample size $n \to \infty$, the generalization error remains bounded below by a positive constant with high probability. Our results hold for arbitrary values of $p \in [1, \infty)$, in contrast to prior results studying the Hilbert space case ($p = 2$) using kernel methods. Our proof uses a geometric argument which identifies harmful neighborhoods of the training data using Sobolev inequalities.
Read the full abstract

All authors Kedar Karhadkar, Alexander Sietsema, Deanna Needell, Guido Montufar

Machine Learning · Cross-listed from stat.ML

Safety-Efficacy Trade Off: Robustness against Data-Poisoning

Backdoor and data poisoning attacks can achieve high attack success while evading existing spectral and optimisation based defences. We show that this behaviour is not incidental, but arises from a fundamental geometric mechanism in input space. Using kernel ridge regression as an exact model of wide neural networks, we prove that clustered dirty label poisons induce a rank one spike in the input Hessian whose magnitude scales quadratically with attack efficacy. Crucially, for nonlinear kernels we identify a near clone regime in which poison efficacy remains order one while the induced input curvature vanishes, making the attack provably spectrally undetectable. We further show that input gradient regularisation contracts poison aligned Fisher and Hessian eigenmodes under gradient flow, yielding an explicit and unavoidable safety efficacy trade off by reducing data fitting capacity. For exponential kernels, this defence admits a precise interpretation as an anisotropic high pass filter that increases the effective length scale and suppresses near clone poisons. Extensive experiments on linear models and deep convolutional networks across MNIST and CIFAR 10 and CIFAR 100 validate the theory, demonstrating consistent lags between attack success and spectral visibility, and showing that regularisation and data augmentation jointly suppress poisoning. Our results establish when backdoors are inherently invisible, and provide the first end to end characterisation of poisoning, detectability, and defence through input space curvature.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Hessian Spectral Analysis at Foundation Model Scale

Accurate Hessian spectra of foundation models have remained out of reach, leading most prior work to rely on small models or strong structural approximations. We show that faithful spectral analysis of the true Hessian is tractable at frontier scale. Using shard-local finite-difference Hessian vector products compatible with Fully Sharded Data Parallelism, we perform stochastic Lanczos quadrature on open-source language models with up to 100B parameters, producing the first large-scale spectral density estimates beyond the sub-10B regime. We characterize the numerical behavior of this pipeline, including finite-difference bias, floating-point noise amplification, and their effect on Krylov stability in fp32 and bf16, and derive practical operating regimes that are validated empirically. We further provide end-to-end runtime and memory scaling laws, showing that full-operator spectral probing incurs only a modest constant-factor overhead over first-order training. Crucially, direct access to the Hessian reveals that widely used block-diagonal curvature approximations can fail catastrophically, exhibiting order-one relative error and poor directional alignment even in mid-scale LLMs. Together, our results demonstrate that foundation-model Hessian spectra are both computable and qualitatively misrepresented by prevailing approximations, opening the door to principled curvature-based analysis at scale.
Read the full abstract

Machine Learning

Mobile Exergames: Activity Recognition Based on Smartphone Sensors

Smartphone sensors can be extremely useful in providing information on the activities and behaviors of persons. Human activity recognition is increasingly used for games, medical, or surveillance. In this paper, we propose a proof-of-concept 2D endless game called Duck Catch & Fit, which implements a detailed activity recognition system that uses a smartphone accelerometer, gyroscope, and magnetometer sensors. The system applies feature extraction and learning mechanism to detect human activities like staying, side movements, and fake side movements. In addition, a voice recognition system is combined to recognize the word "fire" and raise the game's complexity. The results show that it is possible to use machine learning techniques to recognize human activity with high recognition levels. Also, the combination of movement-based and voice-based integrations contributes to a more immersive gameplay.
Read the full abstract

Machine Learning

JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation

LLMs have traditionally scaled along dense dimensions, where performance is coupled with near-linear increases in computational cost. While MoE decouples capacity from compute, it introduces large memory overhead and hardware efficiency challenges. To overcome these, we propose token-indexed parameters as a novel, orthogonal scaling axis that decouple model capacity from FLOPs. Specifically, we introduce Joint-Token (JTok) and Mixture of Joint-Token (JTok-M), which augment Transformer layers with modulation vectors retrieved from auxiliary embedding tables. These vectors modulate the backbone via lightweight, element-wise operations, incurring negligible FLOPs overhead. Extensive experiments on both dense and MoE backbones, spanning from 650M (190M + 460M embedding) to 61B (17B + 44B embedding) total parameters, demonstrate that our approach consistently reduces validation loss and significantly improves downstream task performance (e.g., +4.1 on MMLU, +8.3 on ARC, +8.9 on CEval). Rigorous isoFLOPs analysis further confirms that JTok-M fundamentally shifts the quality-compute Pareto frontier, achieving comparable model quality with 35% less compute relative to vanilla MoE architectures, and we validate that token-indexed parameters exhibit a predictable power-law scaling behavior. Moreover, our efficient implementation ensures that the overhead introduced by JTok and JTok-M remains marginal.
Read the full abstract

All authors Yebin Yang, Huaijin Wu, Fu Guo, Lin Yao, Xiaohan Qin, Jingzhi Wang, Debing Zhang, Junchi Yan

Machine Learning · Cross-listed from stat.ML

Zero-Flow Encoders

Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions. However, few existing works have exploited this unique capability to resolve fine-grained structural details beyond generation tasks. This paper presents a flow-inspired framework for representation learning. First, we demonstrate that a rectified flow trained using independent coupling is zero everywhere at $t=0.5$ if and only if the source and target distributions are identical. We term this property the zero-flow criterion. Second, we show that this criterion can certify conditional independence, thereby extracting sufficient information from the data. Third, we translate this criterion into a tractable, simulation-free loss function that enables learning amortized Markov blankets in graphical models and latent representations in self-supervised learning tasks. Experiments on both simulated and real-world datasets demonstrate the effectiveness of our approach. The code reproducing our experiments can be found at: https://github.com/probabilityFLOW/zfe.
Read the full abstract

All authors Yakun Wang, Leyang Wang, Song Liu, Taiji Suzuki

Machine Learning

Latent Shadows: The Gaussian-Discrete Duality in Masked Diffusion

Masked discrete diffusion is a dominant paradigm for high-quality language modeling where tokens are iteratively corrupted to a mask state, yet its inference efficiency is bottlenecked by the lack of deterministic sampling tools. While diffusion duality enables deterministic distillation for uniform models, these approaches generally underperform masked models and rely on complex integral operators. Conversely, in the masked domain, prior methods typically assume the absence of deterministic trajectories, forcing a reliance on stochastic distillation. To bridge this gap, we establish explicit Masked Diffusion Duality, proving that the masked process arises as the projection of a continuous Gaussian process via a novel maximum-value index preservation mechanism. Furthermore, we introduce Masked Consistency Distillation (MCD), a principled framework that leverages this duality to analytically construct the deterministic coupled trajectories required for consistency distillation, bypassing numerical ODE solvers. This result strictly improves upon prior stochastic distillation methods, achieving a 16$\times$ inference speedup without compromising generation quality. Our findings not only provide a solid theoretical foundation connecting masked and continuous diffusion, but also unlock the full potential of consistency distillation for high-performance discrete generation. Our code is available at https://anonymous.4open.science/r/MCD-70FD.
Read the full abstract

All authors Guinan Chen, Xunpeng Huang, Ying Sun, Shijin Wang, Yanyong Zhang, Chao Wang

Machine Learning

Sporadic Gradient Tracking over Directed Graphs: A Theoretical Perspective on Decentralized Federated Learning

Decentralized Federated Learning (DFL) enables clients with local data to collaborate in a peer-to-peer manner to train a generalized model. In this paper, we unify two branches of work that have separately solved important challenges in DFL: (i) gradient tracking techniques for mitigating data heterogeneity and (ii) accounting for diverse availability of resources across clients. We propose $\textit{Sporadic Gradient Tracking}$ ($\texttt{Spod-GT}$), the first DFL algorithm that incorporates these factors over general directed graphs by allowing (i) client-specific gradient computation frequencies and (ii) heterogeneous and asymmetric communication frequencies. We conduct a rigorous convergence analysis of our methodology with relaxed assumptions on gradient estimation variance and gradient diversity of clients, providing consensus and optimality guarantees for GT over directed graphs despite intermittent client participation. Through numerical experiments on image classification datasets, we demonstrate the efficacy of $\texttt{Spod-GT}$ compared to well-known GT baselines.
Read the full abstract

All authors Shahryar Zehtabi, Dong-Jun Han, Seyyedali Hosseinalipour, Christopher Brinton

Machine Learning

Multi-Objective Multi-Fidelity Bayesian Optimization with Causal Priors

Multi-fidelity Bayesian optimization (MFBO) accelerates the search for the global optimum of black-box functions by integrating inexpensive, low-fidelity approximations. The central task of an MFBO policy is to balance the cost-efficiency of low-fidelity proxies against their reduced accuracy to ensure effective progression toward the high-fidelity optimum. Existing MFBO methods primarily capture associational dependencies between inputs, fidelities, and objectives, rather than causal mechanisms, and can perform poorly when lower-fidelity proxies are poorly aligned with the target fidelity. We propose RESCUE (REducing Sampling cost with Causal Understanding and Estimation), a multi-objective MFBO method that incorporates causal calculus to systematically address this challenge. RESCUE learns a structural causal model capturing causal relationships between inputs, fidelities, and objectives, and uses it to construct a probabilistic multi-fidelity (MF) surrogate that encodes intervention effects. Exploiting the causal structure, we introduce a causal hypervolume knowledge-gradient acquisition strategy to select input-fidelity pairs that balance expected multi-objective improvement and cost. We show that RESCUE improves sample efficiency over state-of-the-art MF optimization methods on synthetic and real-world problems in robotics, machine learning (AutoML), and healthcare.
Read the full abstract

All authors Md Abir Hossen, Mohammad Ali Javidian, Vignesh Narayanan, Jason M. O'Kane, Pooyan Jamshidi

Machine Learning

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time. Existing infinite-horizon methods, which often rely on discounted contraction, do not naturally account for this fixed-horizon structure. We introduce a modified Q-function: rather than targeting the full-horizon, we learn a K-step lookahead Q-function that truncates planning to the next K steps. To further improve sample efficiency, we introduce a thresholding mechanism: actions are selected only when their estimated K-step lookahead value exceeds a time-varying threshold. We provide an efficient tabular learning algorithm for this novel objective, proving it achieves fast finite-sample convergence: it achieves minimax optimal constant regret for $K=1$ and $\mathcal{O}(\max((K-1),C_{K-1})\sqrt{SAT\log(T)})$ regret for any $K \geq 2$. We numerically evaluate the performance of our algorithm under the objective of maximizing reward. Our implementation adaptively increases K over time, balancing lookahead depth against estimation variance. Empirical results demonstrate superior cumulative rewards over state-of-the-art tabular RL methods across synthetic MDPs and RL environments: JumpRiverswim, FrozenLake and AnyTrading. Code is provided on \href{https://github.com/jamie01713/K-Step-Lookahead}{github}.
Read the full abstract