English
Related papers

Related papers: Non-Asymptotic Length Generalization

200 papers

We present algorithms for efficiently learning regularizers that improve generalization. Our approach is based on the insight that regularizers can be viewed as upper bounds on the generalization gap, and that reducing the slack in the…

Machine Learning · Computer Science 2019-02-25 Matthew Streeter

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

This paper investigates the approximation power of three types of random neural networks: (a) infinite width networks, with weights following an arbitrary distribution; (b) finite width networks obtained by subsampling the preceding…

Machine Learning · Computer Science 2019-10-21 Bolton Bailey , Ziwei Ji , Matus Telgarsky , Ruicheng Xian

Pre-trained language models have recently emerged as a powerful tool for fine-tuning a variety of language tasks. Ideally, when models are pre-trained on large amount of data, they are expected to gain implicit knowledge. In this paper, we…

Computation and Language · Computer Science 2023-06-22 Mohamad Ballout , Ulf Krumnack , Gunther Heidemann , Kai-Uwe Kühnberger

Today's large language models (LLMs) typically train on short text segments (e.g., <4K tokens) due to the quadratic complexity of their Transformer architectures. As a result, their performance suffers drastically on inputs longer than…

Computation and Language · Computer Science 2024-06-26 Chi Han , Qifan Wang , Hao Peng , Wenhan Xiong , Yu Chen , Heng Ji , Sinong Wang

Learning to optimize (L2O) has gained increasing popularity, which automates the design of optimizers by data-driven approaches. However, current L2O methods often suffer from poor generalization performance in at least two folds: (i)…

Machine Learning · Computer Science 2023-03-29 Junjie Yang , Tianlong Chen , Mingkang Zhu , Fengxiang He , Dacheng Tao , Yingbin Liang , Zhangyang Wang

We introduce an asymmetric distance in the space of learning tasks, and a framework to compute their complexity. These concepts are foundational for the practice of transfer learning, whereby a parametric model is pre-trained for a task,…

Machine Learning · Computer Science 2020-07-15 Alessandro Achille , Giovanni Paolini , Glen Mbeng , Stefano Soatto

The fundamental result of Li, Long, and Srinivasan on approximations of set systems has become a key tool across several communities such as learning theory, algorithms, computational geometry, combinatorics and data analysis. The goal of…

Machine Learning · Computer Science 2022-09-02 Mónika Csikós , Nabil H. Mustafa

We introduce a new notion of complexity of functions and we show that it has the following properties: (i) it governs a PAC Bayes-like generalization bound, (ii) for neural networks it relates to natural notions of complexity of functions…

Machine Learning · Computer Science 2023-03-15 Grzegorz Głuch , Rudiger Urbanke

Despite the demonstrated empirical efficacy of prompt tuning to adapt a pretrained language model for a new task, the theoretical underpinnings of the difference between "tuning parameters before the input" against "the tuning of model…

Machine Learning · Computer Science 2023-11-17 Yihan Wang , Jatin Chauhan , Wei Wang , Cho-Jui Hsieh

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

Recent studies show that transformer-based architectures emulate gradient descent during a forward pass, contributing to in-context learning capabilities - an ability where the model adapts to new tasks based on a sequence of prompt…

Statistics Theory · Mathematics 2024-05-13 Karthik Duraisamy

We present a new algorithm for general reinforcement learning where the true environment is known to belong to a finite class of N arbitrary models. The algorithm is shown to be near-optimal for all but O(N log^2 N) time-steps with high…

Machine Learning · Computer Science 2013-08-23 Tor Lattimore , Marcus Hutter , Peter Sunehag

Masked language modeling is a widely used method for learning language representations, where the model predicts a randomly masked word in each input. However, this approach typically considers only a single correct answer during training,…

Computation and Language · Computer Science 2025-04-10 Seunghyun Ji , Soowon Lee

To test generalization ability of a class of deep neural networks, we randomly generate a large number of different rule sets for 2-D cellular automata (CA), based on John Conway's Game of Life. Using these rules, we compute several…

Machine Learning · Computer Science 2021-11-22 Marcel Aach , Jens Henrik Goebbert , Jenia Jitsev

Mean-field characterizations of first-order iterative algorithms -- including Approximate Message Passing (AMP), stochastic and proximal gradient descent, and Langevin diffusions -- have enabled a precise understanding of learning dynamics…

Statistics Theory · Mathematics 2025-07-01 Max Lovig , Tianhao Wang , Zhou Fan

Active learning can reduce the number of samples needed to perform a hypothesis test and to estimate the parameters of a model. In this paper, we revisit the work of Chernoff that described an asymptotically optimal algorithm for performing…

Machine Learning · Statistics 2022-03-14 Subhojyoti Mukherjee , Ardhendu Tripathy , Robert Nowak

The use of Transformer architectures has facilitated remarkable progress in speech enhancement. Training Transformers using substantially long speech utterances is often infeasible as self-attention suffers from quadratic complexity. It is…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-18 Qiquan Zhang , Hongxu Zhu , Xinyuan Qian , Eliathamby Ambikairajah , Haizhou Li

M-estimators are ubiquitous in machine learning and statistical learning theory. They are used both for defining prediction strategies and for evaluating their precision. In this paper, we propose the first non-asymptotic "any-time"…

Statistics Theory · Mathematics 2019-05-27 Victor-Emmanuel Brunel , Arnak S. Dalalyan , Nicolas Schreuder

Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data. Such over-fitting ability hinders generalization when mislabeled training examples are present. On the other…

Machine Learning · Computer Science 2020-10-06 Wei Hu , Zhiyuan Li , Dingli Yu
‹ Prev 1 8 9 10 Next ›