English
Related papers

Related papers: Directional Optimization Asymmetry in Transformers…

200 papers

Transformers have shown a remarkable ability for in-context learning (ICL), making predictions based on contextual examples. However, while theoretical analyses have explored this prediction capability, the nature of the inferred context…

Machine Learning · Computer Science 2025-05-20 Fei Lu , Yue Yu

Real-world reinforcement learning is often \emph{nonstationary}: rewards and dynamics drift, accelerate, oscillate, and trigger abrupt switches in the optimal action. Existing theory often represents nonstationarity with coarse-scale models…

Machine Learning · Computer Science 2026-01-30 Zuyuan Zhang , Mahdi Imani , Tian Lan

Inverse design aims to find design parameters $x$ achieving target performance $y^*$. Generative approaches learn bidirectional mappings between designs and labels, enabling diverse solution sampling. However, standard conditional flow…

Machine Learning · Computer Science 2026-03-18 Miguel de Campos , Werner Krebs , Hanno Gottschalk

Whether language models can systematically generalize remains actively debated. Yet empirical performance is jointly shaped by multiple factors such as training data, training paradigms, and inference-time strategies, making failures…

Artificial Intelligence · Computer Science 2026-04-17 Yao Tong , Jiayuan Ye , Anastasia Borovykh , Reza Shokri

In a physical neural system, learning rules must be local both in space and time. In order for learning to occur, non-local information must be communicated to the deep synapses through a communication channel, the deep learning channel. We…

Neural and Evolutionary Computing · Computer Science 2017-12-25 Pierre Baldi , Peter Sadowski , Zhiqin Lu

Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) can…

Machine Learning · Computer Science 2025-06-24 Ju-Seung Byun , Andrew Perrault

Recent empirical results have demonstrated that training large language models (LLMs) with negative-only feedback can match or exceed standard reinforcement learning from human feedback (RLHF). Negative Sample Reinforcement achieves parity…

Artificial Intelligence · Computer Science 2026-03-18 Quan Cheng

Self-improvement through post-training methods such as iterative preference learning has been acclaimed for enhancing the problem-solving capabilities (e.g., mathematical reasoning) of Large Language Models (LLMs) without human…

Computation and Language · Computer Science 2024-07-09 Ting Wu , Xuefeng Li , Pengfei Liu

Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can solve an unseen task by utilizing task-specific prompts without…

Machine Learning · Computer Science 2023-10-10 Yu Huang , Yuan Cheng , Yingbin Liang

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…

Reactive synthesis algorithms allow automatic construction of policies to control an environment modeled as a Markov Decision Process (MDP) that are optimal with respect to high-level temporal logic specifications. However, they assume that…

Formal Languages and Automata Theory · Computer Science 2022-05-31 Rajeev Alur , Suguman Bansal , Osbert Bastani , Kishor Jothimurugan

Intrinsic self-correction refers to the phenomenon where a language model refines its own outputs purely through prompting, without external feedback or parameter updates. While this approach improves performance across diverse tasks, its…

Computation and Language · Computer Science 2026-02-12 Yu-Ting Lee , Fu-Chieh Chang , Yu-En Shu , Hui-Ying Shih , Pei-Yuan Wu

We investigate the ability of transformers to perform in-context reinforcement learning (ICRL), where a model must infer and execute learning algorithms from trajectory data without parameter updates. We show that a linear self-attention…

Machine Learning · Statistics 2026-05-08 Haodong Liang , Lifeng Lai

Time series forecasting faces two important but often overlooked challenges. Firstly, the inherent random noise in the time series labels sets a theoretical lower bound for the forecasting error, which is positively correlated with the…

Machine Learning · Computer Science 2025-09-26 Tianyi Shi , Zhu Meng , Yue Chen , Siyang Zheng , Fei Su , Jin Huang , Changrui Ren , Zhicheng Zhao

Text-to-image diffusion models can generate stunning visuals, yet they often fail at tasks children find trivial--like placing a dog to the right of a teddy bear rather than to the left. When combinations get more unusual--a giraffe above…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Sapir Esther Yiflach , Yuval Atzmon , Gal Chechik

Self-attention is essential to Transformer architectures, yet how information is embedded in the self-attention matrices and how different objective functions impact this process remains unclear. We present a mathematical framework to…

Machine Learning · Computer Science 2025-06-04 Matteo Saponati , Pascal Sager , Pau Vilimelis Aceituno , Thilo Stadelmann , Benjamin Grewe

Low-rank structure is a common implicit assumption in many modern reinforcement learning (RL) algorithms. For instance, reward-free and goal-conditioned RL methods often presume that the successor measure admits a low-rank representation.…

Machine Learning · Computer Science 2025-11-06 Bastien Dubail , Stefan Stojanovic , Alexandre Proutière

Deep learning has shown that learned functions can dramatically outperform hand-designed functions on perceptual tasks. Analogously, this suggests that learned optimizers may similarly outperform current hand-designed optimizers, especially…

Neural and Evolutionary Computing · Computer Science 2019-06-11 Luke Metz , Niru Maheswaranathan , Jeremy Nixon , C. Daniel Freeman , Jascha Sohl-Dickstein

Transformer-based sequence-to-sequence architectures, while achieving state-of-the-art results on a large number of NLP tasks, can still suffer from overfitting during training. In practice, this is usually countered either by applying…

Computation and Language · Computer Science 2022-01-04 Dušan Variš , Ondřej Bojar

Although Transformer has made breakthrough success in widespread domains especially in Natural Language Processing (NLP), applying it to time series forecasting is still a great challenge. In time series forecasting, the autoregressive…

Machine Learning · Computer Science 2021-06-01 Kai Chen , Guang Chen , Dan Xu , Lijun Zhang , Yuyao Huang , Alois Knoll