English
Related papers

Related papers: Non-Asymptotic Length Generalization

200 papers

Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been…

Machine Learning · Statistics 2018-01-03 Elad Hoffer , Itay Hubara , Daniel Soudry

We introduce a new measure on regular languages: their nondeterministic syntactic complexity. It is the least degree of any extension of the `canonical boolean representation' of the syntactic monoid. Equivalently, it is the least number of…

Formal Languages and Automata Theory · Computer Science 2021-01-12 Robert Myers , Stefan Milius , Henning Urbat

Multi-step cloth manipulation is a challenging problem for robots due to the high-dimensional state spaces and the dynamics of cloth. Despite recent significant advances in end-to-end imitation learning for multi-step cloth manipulation…

Robotics · Computer Science 2025-03-07 Hanyi Zhao , Jinxuan Zhu , Zihao Yan , Yichen Li , Yuhong Deng , Xueqian Wang

We study a generalization of deduplication, which enables lossless deduplication of highly similar data and show that standard deduplication with fixed chunk length is a special case. We provide bounds on the expected length of coded…

Information Theory · Computer Science 2020-03-04 Rasmus Vestergaard , Qi Zhang , Daniel E. Lucani

This paper explores the generalization characteristics of iterative learning algorithms with bounded updates for non-convex loss functions, employing information-theoretic techniques. Our key contribution is a novel bound for the…

Machine Learning · Computer Science 2023-10-17 Jingwen Fu , Nanning Zheng

Average-case analysis computes the complexity of an algorithm averaged over all possible inputs. Compared to worst-case analysis, it is more representative of the typical behavior of an algorithm, but remains largely unexplored in…

Optimization and Control · Mathematics 2021-10-05 Courtney Paquette , Bart van Merriënboer , Elliot Paquette , Fabian Pedregosa

One of the fundamental challenges in the deep learning community is to theoretically understand how well a deep neural network generalizes to unseen data. However, current approaches often yield generalization bounds that are either too…

Machine Learning · Computer Science 2024-07-23 Chengli Tan , Jiangshe Zhang , Junmin Liu

We present a few classes of synchronizing automata exhibiting certain extremal properties with regard to synchronization. The first is a series of automata with subsets whose shortest extending words are of length $\varTheta(n^2)$, where…

Formal Languages and Automata Theory · Computer Science 2016-08-04 Andrzej Kisielewicz , Marek Szykuła

Deep Neural Networks can generalize despite being significantly overparametrized. Recent research has tried to examine this phenomenon from various view points and to provide bounds on the generalization error or measures predictive of the…

Machine Learning · Computer Science 2020-12-07 Parth Natekar , Manik Sharma

Error bounds and complexity bounds in numerical analysis and information-based complexity are often proved for functions that are defined on very simple domains, such as a cube, a torus, or a sphere. We study optimal error bounds for the…

Numerical Analysis · Mathematics 2020-01-15 Erich Novak

Learned optimizers (LOs) have the potential to significantly reduce the wall-clock training time of neural networks. However, they can struggle to optimize unseen tasks (meta-generalize), especially when training networks wider than those…

Machine Learning · Computer Science 2026-03-20 Benjamin Thérien , Charles-Étienne Joseph , Boris Knyazev , Edouard Oyallon , Irina Rish , Eugene Belilovsky

The ability to abstract, count, and use System~2 reasoning are well-known manifestations of intelligence and understanding. In this paper, we argue, using the example of the ``Look and Say" puzzle, that although deep neural networks can…

Artificial Intelligence · Computer Science 2022-03-22 Wlodek W. Zadrozny

Can transformers learn to perform algorithmic tasks reliably across previously unseen input/output domains? While pre-trained language models show solid accuracy on benchmarks incorporating algorithmic reasoning, assessing the reliability…

Machine Learning · Computer Science 2025-07-22 Michal Spiegel , Michal Štefánik , Marek Kadlčík , Josef Kuchař

Machine learning models with inputs in a Euclidean space $\mathbb{R}^d$, when implemented on digital computers, generalize, and their generalization gap converges to $0$ at a rate of $c/N^{1/2}$ concerning the sample size $N$. However, the…

Machine Learning · Computer Science 2026-05-14 Anastasis Kratsios , A. Martina Neuman , Gudmund Pammer

Modern deep neural networks (DNNs) represent a formidable challenge for theorists: according to the commonly accepted probabilistic framework that describes their performance, these architectures should overfit due to the huge number of…

Disordered Systems and Neural Networks · Physics 2022-03-03 S. Ariosto , R. Pacelli , F. Ginelli , M. Gherardi , P. Rotondo

The foundations of deep learning are supported by the seemingly opposing perspectives of approximation or learning theory. The former advocates for large/expressive models that need not generalize, while the latter considers classes that…

Machine Learning · Computer Science 2025-06-27 Ruiyang Hong , Anastasis Kratsios

The theory of asymptotic complexity provides an approach to characterizing the behavior of programs in terms of bounds on the number of computational steps executed or use of computational resources. We describe work using ACL2 to prove…

Computational Complexity · Computer Science 2022-05-25 William D. Young

In this work, we empirically show that updating pretrained LMs (350M, 1.3B, 2.7B) with just a few steps of Gradient Ascent Post-training (GAP) on random, unlabeled text corpora enhances its zero-shot generalization capabilities across…

Computation and Language · Computer Science 2023-06-13 Dongkeun Yoon , Joel Jang , Sungdong Kim , Minjoon Seo

An ongoing challenge in neural information processing is: how do neurons adjust their connectivity to improve task performance over time (i.e., actualize learning)? It is widely believed that there is a consistent, synaptic-level learning…

Neural and Evolutionary Computing · Computer Science 2021-06-01 Aman Bhargava , Mohammad R. Rezaei , Milad Lankarany

Chain-of-Thought (CoT) has been shown to empirically improve Transformers' performance, and theoretically increase their expressivity to Turing completeness. However, whether Transformers can learn to generalize to CoT traces longer than…

Machine Learning · Computer Science 2026-04-29 Oliver Kraus , Yash Sarrof , Yuekun Yao , Alexander Koller , Michael Hahn
‹ Prev 1 4 5 6 7 8 10 Next ›