English
Related papers

Related papers: Energy-Entropy Regularization: The True Power of M…

200 papers

Large language models (LLMs) exhibit a wide range of capabilities, including mathematical reasoning, code generation, and linguistic behaviors. We show that many capabilities are highly localized to small subsets of attention heads within…

Computation and Language · Computer Science 2026-03-05 Anna Bair , Yixuan Even Xu , Mingjie Sun , J. Zico Kolter

At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to…

Transformers have demonstrated impressive in-context learning (ICL) capabilities, raising the question of whether they can serve as metalearners that adapt to new tasks using only a small number of in-context examples, without any further…

Machine Learning · Computer Science 2025-10-23 Roey Magen , Gal Vardi

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…

Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…

Machine Learning · Computer Science 2026-03-24 Hung-Hsuan Chen

Transformer-based models have achieved remarkable performance in NLP tasks. However, their structural characteristics-multiple layers and attention heads-introduce efficiency challenges in inference and deployment. To address these…

Computation and Language · Computer Science 2026-02-03 Minsik Choi , Hyegang Son , Changhoon Kim , Young Geun Kim

The statistical essence of the Transformer architecture has long remained elusive: Is it a universal approximator, or a neural network version of known computational algorithms? Through rigorous algebraic proof, we show that the latter…

Machine Learning · Computer Science 2026-04-16 Xiaojun Tan , Yuchen Zhao

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

Many reinforcement learning (RL) algorithms are too costly to use in practice due to the large sizes $S, A$ of the problem's state and action space. To resolve this issue, we study transfer RL with latent low rank structure. We consider the…

Machine Learning · Computer Science 2024-10-30 Tyler Sam , Yudong Chen , Christina Lee Yu

Computation, mechanics and materials merge in biological systems, which can continually self-optimize through internal adaptivity across length scales, from cytoplasm and biofilms to animal herds. Recent interest in such material-based…

Soft Condensed Matter · Physics 2023-04-19 Vishal P. Patil , Ian Ho , Manu Prakash

We introduce "AnnealSGD", a regularized stochastic gradient descent algorithm motivated by an analysis of the energy landscape of a particular class of deep networks with sparse random weights. The loss function of such networks can be…

Machine Learning · Computer Science 2017-04-25 Pratik Chaudhari , Stefano Soatto

Attention-based transformers have achieved tremendous success across a variety of disciplines including natural languages. To deepen our understanding of their sequential modeling capabilities, there is a growing interest in using Markov…

Machine Learning · Computer Science 2025-07-22 Ashok Vardhan Makkuva , Marco Bondaschi , Adway Girish , Alliot Nagle , Martin Jaggi , Hyeji Kim , Michael Gastpar

Transformer architectures are designed by trial and error: the number of attention heads, the depth, and the head size are fixed before training begins, with no mathematical principle to guide the choice. The result is systematic structural…

Machine Learning · Computer Science 2026-04-14 Giansalvo Cirrincione

Given a renormalization scheme, we show how to formulate a tractable convex relaxation of the set of feasible local density matrices of a many-body quantum system. The relaxation is obtained by introducing a hierarchy of constraints between…

Quantum Physics · Physics 2024-04-11 Ilya Kull , Norbert Schuch , Ben Dive , Miguel Navascués

One of the central challenges in modern machine learning is understanding how neural networks generalize knowledge learned from training data to unseen test data. While numerous empirical techniques have been proposed to improve…

Machine Learning · Computer Science 2025-04-18 Entao Yang , Xiaotian Zhang , Yue Shang , Ge Zhang

Modern neural networks exhibit a striking property: basins of attraction in the loss landscape are often connected by low-loss paths, yet optimization dynamics generally remain confined to a single convex basin and rarely explore…

Machine Learning · Computer Science 2026-03-13 Luca Di Carlo , Chase Goddard , David J. Schwab

Large Language Models demonstrate remarkable mathematical capabilities but at the same time struggle with abstract reasoning and planning. In this study, we explore whether Transformers can learn to abstract and generalize the rules…

Neural and Evolutionary Computing · Computer Science 2024-12-03 Mikhail Burtsev

Recent advancements in cognitive science and multi-round reasoning techniques for Large Language Models (LLMs) suggest that iterative thinking processes improve problem-solving performance in complex tasks. Inspired by this, approaches like…

Artificial Intelligence · Computer Science 2025-03-06 Chenhui Xu , Dancheng Liu , Jiajie Li , Amir Nassereldine , Zhaohui Li , Jinjun Xiong

In distributed applications, such as energy demand forecasting at the substation level or federated learning, a large number of related tasks must be learned by different models, while the exact task relationships are unknown. We propose…

Machine Learning · Computer Science 2026-05-25 Eloi Campagne , Yvenn Amara-Ouali , Yannig Goude , Mathilde Mougeot , Argyris Kalogeratos

Flat regions of the neural network loss landscape have long been hypothesized to correlate with better generalization properties. A closely related but distinct problem is training models that are robust to internal perturbations to their…

Machine Learning · Computer Science 2026-02-10 Philip Jacobson , Ben Feinberg , Suhas Kumar , Sapan Agarwal , T. Patrick Xiao , Christopher Bennett