English
Related papers

Related papers: Non-Asymptotic Length Generalization

200 papers

Characterizing precisely the asymptotic generalization error of neural networks using parameters that can be estimated efficiently is a crucial problem in machine learning, which relies heavily on heuristics and practitioners' intuition to…

Machine Learning · Computer Science 2026-05-22 David Perera , Victor Moura , Lais Isabelle Alves dos Santos , Michel F. C. Haddad , Flavio Figueiredo

Motivated by the learned iterative soft thresholding algorithm (LISTA), we introduce a general class of neural networks suitable for sparse reconstruction from few linear measurements. By allowing a wide range of degrees of weight-sharing…

Machine Learning · Computer Science 2022-01-19 Ekkehard Schnoor , Arash Behboodi , Holger Rauhut

Recurrent Neural Network (RNN) is a fundamental structure in deep learning. Recently, some works study the training process of over-parameterized neural networks, and show that over-parameterized networks can learn functions in some notable…

Machine Learning · Computer Science 2022-01-27 Lifu Wang , Bo Shen , Bo Hu , Xing Cao

Universal Approximation Theorems establish the density of various classes of neural network function approximators in $C(K, \mathbb{R}^m)$, where $K \subset \mathbb{R}^n$ is compact. In this paper, we aim to extend these guarantees by…

Machine Learning · Statistics 2022-12-16 Naveen Durvasula

At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our…

Machine Learning · Computer Science 2020-05-04 Melikasadat Emami , Mojtaba Sahraee-Ardakan , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

The Minimum Description Length (MDL) principle offers a formal framework for applying Occam's razor in machine learning. However, its application to neural networks such as Transformers is challenging due to the lack of a principled,…

Machine Learning · Computer Science 2026-03-04 Peter Shaw , James Cohan , Jacob Eisenstein , Kristina Toutanova

We characterize the complexity functions of subshifts up to asymptotic equivalence. The complexity function of every aperiodic function is non-decreasing, submultiplicative and grows at least linearly. We prove that conversely, every…

Dynamical Systems · Mathematics 2025-09-24 Be'eri Greenfeld , Carlos Gustavo Moreira , Efim Zelmanov

Imitation learning holds the promise of equipping robots with versatile skills by learning from expert demonstrations. However, policies trained on finite datasets often struggle to generalize beyond the training distribution. In this work,…

Machine Learning · Computer Science 2025-04-28 Yixiao Wang

We prove a new asymptotic un-equipartition property for the perplexity of long texts generated by a language model and present supporting experimental evidence from open-source models. Specifically we show that the logarithmic perplexity of…

Computation and Language · Computer Science 2025-09-15 Tyler Bell , Avinash Mudireddy , Ivan Johnson-Eversoll , Soura Dasgupta , Raghu Mudumbai

In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction. NTP takes as input a task specification (e.g.,…

Artificial Intelligence · Computer Science 2018-03-16 Danfei Xu , Suraj Nair , Yuke Zhu , Julian Gao , Animesh Garg , Li Fei-Fei , Silvio Savarese

A key property of neural networks is their capacity of adapting to data during training. Yet, our current mathematical understanding of feature learning and its relationship to generalization remain limited. In this work, we provide a…

Machine Learning · Statistics 2024-10-25 Yatin Dandi , Luca Pesce , Hugo Cui , Florent Krzakala , Yue M. Lu , Bruno Loureiro

In this paper, we provide a new framework to obtain the generalization bounds of the learning process for domain adaptation, and then apply the derived bounds to analyze the asymptotical convergence of the learning process. Without loss of…

Machine Learning · Computer Science 2013-04-08 Chao Zhang , Lei Zhang , Jieping Ye

In this paper, we investigate the inherent capabilities of transformer models in learning arithmetic algorithms, such as addition and parity. Through experiments and attention analysis, we identify a number of crucial factors for achieving…

Machine Learning · Computer Science 2024-05-13 Shaoxiong Duan , Yining Shi , Wei Xu

Previous research has sought to enhance the graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data. While these led to specialized LLMs better at solving graph algorithm problems, we don't need LLMs for…

Machine Learning · Computer Science 2025-08-19 Yizhuo Zhang , Heng Wang , Shangbin Feng , Zhaoxuan Tan , Xinyun Liu , Yulia Tsvetkov

Parikh's theorem states that every Context Free Language (CFL) has the same Parikh image as that of a regular language. A finite state automaton accepting such a regular language is called a Parikh-equivalent automaton. In the worst case,…

Formal Languages and Automata Theory · Computer Science 2011-09-27 M. Praveen

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Normalization techniques such as Batch Normalization have been applied successfully for training deep neural networks. Yet, despite its apparent empirical benefits, the reasons behind the success of Batch Normalization are mostly…

Machine Learning · Statistics 2018-10-09 Jonas Kohler , Hadi Daneshmand , Aurelien Lucchi , Ming Zhou , Klaus Neymeyr , Thomas Hofmann

We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer…

Machine Learning · Computer Science 2017-11-22 Kenji Kawaguchi , Bo Xie , Vikas Verma , Le Song

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak

Length generalization, the ability to solve problems longer than those seen during training, remains a critical challenge for large language models (LLMs). Previous work modifies positional encodings (PEs) and data formats to improve length…

Computation and Language · Computer Science 2025-05-20 Yi Hu , Shijia Kang , Haotong Yang , Haotian Xu , Muhan Zhang