🤖 Category

cs.LG

2043 papers

CTRL Your Shift: Clustered Transfer Residual Learning for Many Small Datasets

This paper introduces Clustered Transfer Residual Learning (CTRL), a meta-learning method that combines cross-domain residual learning with adaptive clustering to improve prediction accuracy and preserve source-level heterogeneity across numerous small datasets with distributional shifts, demonstrating superior performance over state-of-the-art benchmarks on five large-scale datasets including a Swiss asylum resettlement program.

Gauri Jain, Dominik Rothenhäusler, Kirk Bansak, Elisabeth PaulsonWed, 11 Ma🤖 cs.LG

Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies

This paper introduces Multimodal Large Language Model-assisted Evolutionary Search (MLES), a novel framework that combines multimodal LLMs with evolutionary search and visual feedback to automatically generate transparent, verifiable, and human-aligned programmatic control policies that match the performance of deep reinforcement learning methods like PPO.

Qinglong Hu, Xialiang Tong, Mingxuan Yuan, Fei Liu, Zhichao Lu, Qingfu ZhangWed, 11 Ma🤖 cs.LG

Operator Learning for Consolidation: An Architectural Comparison for DeepONet Variants

This study systematically evaluates and enhances DeepONet architectures for geotechnical consolidation problems, demonstrating that a physics-inspired, Fourier feature-enhanced model (Model 4) significantly outperforms standard configurations and achieves up to 1,000-fold computational speedups in 3D scenarios, thereby enabling efficient uncertainty quantification and advancing the integration of scientific machine learning in geotechnics.

Yongjin Choi, Chenying Liu, Jorge MacedoWed, 11 Ma🤖 cs.LG

FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization

The paper introduces FrontierCO, a large-scale benchmark utilizing real-world and competition-grade datasets across eight combinatorial optimization problems to rigorously evaluate ML solvers against classical methods, revealing a persistent performance gap on extreme-scale instances while identifying specific scenarios where ML approaches excel.

Shengyu Feng, Weiwei Sun, Shanda Li, Ameet Talwalkar, Yiming YangWed, 11 Ma🤖 cs.LG

A Systematic Evaluation of On-Device LLMs: Quantization, Performance, and Resources

This paper presents a systematic evaluation of on-device Large Language Models across various sizes and quantization methods, revealing that heavily quantized larger models outperform smaller high-precision ones beyond a 3.5 bits-per-weight threshold while identifying a shift from communication to computational constraints as model size decreases.

Qingyu Song, Rui Liu, Wei Lin, Peiyu Liao, Wenqian Zhao, Yiwen Wang, Shoubo Hu, Yining Jiang, Mochun Long, Hui-Ling Zhen, Ning Jiang, Mingxuan Yuan, Qiao Xiang, Hong XuWed, 11 Ma🤖 cs.LG

The Gaussian-Multinoulli Restricted Boltzmann Machine: A Potts Model Extension of the GRBM

This paper introduces the Gaussian-Multinoulli Restricted Boltzmann Machine (GM-RBM), a generative model that extends the standard GB-RBM by employing q-state Potts hidden units to better capture discrete, structured representations, demonstrating competitive performance on analogical recall and memory benchmarks while offering a scalable alternative to binary latent models.

Nikhil Kapasi, Mohamed Elfouly, William Whitehead, Luke TheogarajanWed, 11 Ma🤖 cs.LG

Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning

The paper introduces Scalable Message Passing Neural Networks (SMPNNs), a deep Graph Neural Network architecture that replaces computationally expensive attention mechanisms with standard convolutional message passing within a Pre-Layer Normalization Transformer-style block, achieving state-of-the-art performance on large graphs while theoretically addressing oversmoothing through the necessity of residual connections for universal approximation.

Haitz Sáez de Ocáriz Borde, Artem Lukoianov, Anastasis Kratsios, Michael Bronstein, Xiaowen DongWed, 11 Ma🤖 cs.LG

Unsupervised Representation Learning from Sparse Transformation Analysis

This paper proposes an unsupervised representation learning framework that factorizes latent variable transformations into sparse rotational and potential flow fields, enabling the model to learn disentangled representations based on independent transformation primitives while achieving state-of-the-art performance in data likelihood and equivariance on sequence data.

Yue Song, Thomas Anderson Keller, Yisong Yue, Pietro Perona, Max WellingWed, 11 Ma🤖 cs.LG

ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning

The paper introduces ARLBench, a flexible and efficient benchmark for hyperparameter optimization in reinforcement learning that utilizes a representative subset of tasks to enable cost-effective comparisons of diverse AutoRL methods and lower the barrier to entry for researchers with limited compute resources.

Jannis Becktepe, Julian Dierkes, Carolin Benjamins, Aditya Mohan, David Salinas, Raghu Rajan, Frank Hutter, Holger Hoos, Marius Lindauer, Theresa EimerWed, 11 Ma🤖 cs.LG

Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets

This paper proves that randomly initialized, polynomially over-parameterized convolutional neural networks contain structured subnetworks capable of approximating smaller networks without training, by developing new mathematical tools to overcome previous limitations in analyzing the Strong Lottery Ticket Hypothesis for structured pruning.

Arthur da Cunha, Francesco d'Amore, Emanuele NataleWed, 11 Ma🤖 cs.LG