English
Related papers

Related papers: Sometimes I am a Tree: Data Drives Unstable Hierar…

200 papers

The ability to reason with multiple hierarchical structures is an attractive and desirable property of sequential inductive biases for natural language processing. Do the state-of-the-art Transformers and LSTM architectures implicitly…

Computation and Language · Computer Science 2021-11-30 Bill Tuck Weng Pung , Alvin Chan

Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other. This is partly due to the fact that they do not learn in a compositional way, that is, by discovering skills that are shared…

Artificial Intelligence · Computer Science 2018-07-27 Adam Liška , Germán Kruszewski , Marco Baroni

Traditional analyses of gradient descent optimization show that, when the largest eigenvalue of the loss Hessian - often referred to as the sharpness - is below a critical learning-rate threshold, then training is 'stable' and training loss…

Machine Learning · Computer Science 2024-12-24 Lawrence Wang , Stephen J. Roberts

We demonstrate, both analytically and numerically, that learning dynamics of neural networks is generically attracted towards a self-organized critical state. The effect can be modeled with quartic interactions between non-trainable…

Statistical Mechanics · Physics 2021-07-09 Mikhail I. Katsnelson , Vitaly Vanchurin , Tom Westerhout

Machine learning (ML) models have difficulty generalizing when the number of training class instances are numerically imbalanced. The problem of generalization in the face of data imbalance has largely been attributed to the lack of…

Machine Learning · Computer Science 2024-07-16 Damien A. Dablain , Nitesh V. Chawla

Modular neural networks outperform nonmodular neural networks on tasks ranging from visual question answering to robotics. These performance improvements are thought to be due to modular networks' superior ability to model the compositional…

Machine Learning · Computer Science 2025-03-12 Akhilan Boopathy , Sunshine Jiang , William Yue , Jaedong Hwang , Abhiram Iyer , Ila Fiete

The effectiveness of Reinforcement Learning (RL) in Large Language Models (LLMs) depends on the nature and diversity of the data used before and during RL. In particular, reasoning problems can often be approached in multiple ways that rely…

Artificial Intelligence · Computer Science 2026-05-12 Aswin RRV , Jacob Dineen , Divij Handa , Mihir Parmar , Ben Zhou , Swaroop Mishra , Chitta Baral

Scalable probabilistic modeling and prediction in high dimensional multivariate time-series is a challenging problem, particularly for systems with hidden sources of dependence and/or homogeneity. Examples of such problems include dynamic…

Social and Information Networks · Computer Science 2016-06-07 Forough Arabshahi , Furong Huang , Animashree Anandkumar , Carter T. Butts , Sean M. Fitshugh

Mixup, which creates synthetic training instances by linearly interpolating random sample pairs, is a simple and yet effective regularization technique to boost the performance of deep models trained with SGD. In this work, we report a…

Machine Learning · Computer Science 2023-03-03 Zixuan Liu , Ziqiao Wang , Hongyu Guo , Yongyi Mao

Large transformer-based models are able to perform in-context few-shot learning, without being explicitly trained for it. This observation raises the question: what aspects of the training regime lead to this emergent behavior? Here, we…

Weak-to-strong generalization refers to the phenomenon where a stronger model trained under supervision from a weaker one can outperform its teacher. While prior studies aim to explain this effect, most theoretical insights are limited to…

Machine Learning · Computer Science 2025-10-30 Junsoo Oh , Jerry Song , Chulhee Yun

Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution…

Machine Learning · Computer Science 2022-09-13 Damien Teney , Ehsan Abbasnejad , Simon Lucey , Anton van den Hengel

A probability model exhibits instability if small changes in a data outcome result in large, and often unanticipated, changes in probability. This instability is a property of the probability model, given by a distributional form and a…

Statistics Theory · Mathematics 2019-11-18 Andee Kaplan , Daniel Nordman , Stephen Vardeman

Regularization is a technique to improve generalization of machine learning (ML) models. A common form of regularization in the ML literature is to train on data where similar inputs map to different outputs. This improves generalization by…

Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory and chaotic behavior. Empirically, this regime often yields improved…

Machine Learning · Computer Science 2026-04-22 Mario Tuci , Caner Korkmaz , Umut Şimşekli , Tolga Birdal

A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that…

Artificial Intelligence · Computer Science 2026-04-09 Qihan Ren , Peng Wang , Ruikun Cai , Shuai Shao , Dadi Guo , Yuejin Xie , Yafu Li , Quanshi Zhang , Xia Hu , Jing Shao , Dongrui Liu

In-context learning (ICL) enables large language models (LLMs) to perform new tasks by prompting them with a sequence of training examples. However, it is known that ICL is very sensitive to the choice of training examples: randomly…

Computation and Language · Computer Science 2023-09-13 Ting-Yun Chang , Robin Jia

We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well…

Computation and Language · Computer Science 2020-10-07 Xusen Yin , Ralph Weischedel , Jonathan May

High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitative measurements establishing these properties are scarce.…

Machine Learning · Statistics 2025-03-04 Antonio Sclocchi , Alessandro Favero , Noam Itzhak Levi , Matthieu Wyart

Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high…

Machine Learning · Computer Science 2018-05-03 Ludwig Schmidt , Shibani Santurkar , Dimitris Tsipras , Kunal Talwar , Aleksander Mądry
‹ Prev 1 3 4 5 6 7 10 Next ›