English
Related papers

Related papers: Non-Asymptotic Length Generalization

200 papers

Neural networks offer good approximation to many tasks but consistently fail to reach perfect generalization, even when theoretical work shows that such perfect solutions can be expressed by certain architectures. Using the task of formal…

Computation and Language · Computer Science 2024-06-07 Nur Lan , Emmanuel Chemla , Roni Katzir

Length generalization remains a persistent challenge for neural networks: recurrent models tend to suffer from positional biases, while transformers are constrained by fixed computational depth. Regular languages provide a frequently used…

Machine Learning · Computer Science 2026-05-26 Charles Pert , Dalal Alrajeh , Alessandra Russo

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…

Length Generalization is the essential capacity of autonomous agents to perform tasks in longer contexts than those encountered during training. To systematically study this feat, we test how well models can approximate the next token…

Length generalization (LG) is a challenging problem in learning to reason. It refers to the phenomenon that when trained on reasoning problems of smaller lengths or sizes, the resulting model struggles with problems of larger sizes or…

Artificial Intelligence · Computer Science 2024-04-02 Changnan Xiao , Bing Liu

Meta-learning, or "learning to learn", refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key…

Machine Learning · Computer Science 2021-02-24 Sharu Theresa Jose , Osvaldo Simeone

Systematic generalization refers to the capacity to understand and generate novel combinations from known components. Despite recent progress by large language models (LLMs) across various domains, these models often fail to extend their…

Artificial Intelligence · Computer Science 2026-02-27 Philipp Mondorf , Shijia Zhou , Monica Riedler , Barbara Plank

How well do neural networks generalize? Even for grammar induction tasks, where the target generalization is fully known, previous works have left the question open, testing very limited ranges beyond the training set and using different…

Computation and Language · Computer Science 2023-08-28 Nur Lan , Emmanuel Chemla , Roni Katzir

This work is a survey of the main results reported for the degree of extension of two models defining non-regular languages, namely the context-free grammar and the extended automaton over groups. More precisely, we recall the main results…

Formal Languages and Automata Theory · Computer Science 2023-09-07 Victor Mitrana , Mihaela Păun

This paper presents a novel information-theoretic perspective on generalization in machine learning by framing the learning problem within the context of lossy compression and applying finite blocklength analysis. In our approach, the…

Machine Learning · Computer Science 2026-02-05 Kosuke Sugiyama , Masato Uchida

We consider the problem of length generalization in sequence prediction. We define a new metric of performance in this setting -- the Asymmetric-Regret -- which measures regret against a benchmark predictor with longer context length than…

Machine Learning · Computer Science 2024-11-05 Annie Marsden , Evan Dogariu , Naman Agarwal , Xinyi Chen , Daniel Suo , Elad Hazan

In sparse linear regression, the SLOPE estimator generalizes LASSO by penalizing different coordinates of the estimate according to their magnitudes. In this paper, we present a precise performance characterization of SLOPE in the…

Information Theory · Computer Science 2021-06-07 Hong Hu , Yue M. Lu

Conformal prediction provides prediction sets with coverage guarantees. The informativeness of conformal prediction depends on its efficiency, typically quantified by the expected size of the prediction set. Prior work on the efficiency of…

Machine Learning · Computer Science 2026-03-06 Yunzhen Yao , Lie He , Michael Gastpar

Generalization is a central aspect of learning theory. Here, we propose a framework that explores an auxiliary task-dependent notion of generalization, and attempts to quantitatively answer the following question: given two sets of patterns…

Disordered Systems and Neural Networks · Physics 2020-01-08 Francesco Borra , Marco Cosentino Lagomarsino , Pietro Rotondo , Marco Gherardi

Neural networks have achieved remarkable success in many cognitive tasks. However, when they are trained sequentially on multiple tasks without access to old data, their performance on early tasks tend to drop significantly. This problem is…

Machine Learning · Computer Science 2021-02-10 Dong Yin , Mehrdad Farajtabar , Ang Li , Nir Levine , Alex Mott

We investigate the generalization and optimization properties of shallow neural-network classifiers trained by gradient descent in the interpolating regime. Specifically, in a realizable scenario where model weights can achieve arbitrarily…

Machine Learning · Statistics 2023-03-29 Hossein Taheri , Christos Thrampoulidis

We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models store substantial factual knowledge and rules, they often fail to compose this knowledge…

Computation and Language · Computer Science 2026-04-10 Harsh Kohli , Srinivasan Parthasarathy , Huan Sun , Yuekun Yao

Large language models display remarkable capabilities in logical and mathematical reasoning, allowing them to solve complex tasks. Interestingly, these abilities emerge in networks trained on the simple task of next-token prediction. In…

Machine Learning · Computer Science 2024-07-31 Eran Malach

We train neural networks to optimize a Minimum Description Length score, i.e., to balance between the complexity of the network and its accuracy at a task. We show that networks optimizing this objective function master tasks involving…

Computation and Language · Computer Science 2022-04-01 Nur Lan , Michal Geyer , Emmanuel Chemla , Roni Katzir

We are interested in understanding how well Transformer language models (TLMs) can perform reasoning tasks when trained on knowledge encoded in the form of natural language. We investigate their systematic generalization abilities on a…

Machine Learning · Computer Science 2020-10-22 Nicolas Gontier , Koustuv Sinha , Siva Reddy , Christopher Pal