English
Related papers

Related papers: Tight conditions for when the NTK approximation is…

200 papers

Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…

Machine Learning · Computer Science 2026-02-24 Halil Alperen Gozeten , M. Emrullah Ildiz , Xuechen Zhang , Mahdi Soltanolkotabi , Marco Mondelli , Samet Oymak

Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning…

Machine Learning · Computer Science 2020-03-05 Pan Xu , Quanquan Gu

The study of deep neural networks (DNNs) in the infinite-width limit, via the so-called neural tangent kernel (NTK) approach, has provided new insights into the dynamics of learning, generalization, and the impact of initialization. One key…

Machine Learning · Computer Science 2021-06-16 Sina Alemohammad , Zichao Wang , Randall Balestriero , Richard Baraniuk

In this paper we initiate the study of the computational complexity of learning linear temporal logic (LTL) formulas from examples. We construct approximation algorithms for fragments of LTL and prove hardness results; in particular we…

Formal Languages and Automata Theory · Computer Science 2021-02-02 Nathanaël Fijalkow , Guillaume Lagarde

We give a simple proof for the global convergence of gradient descent in training deep ReLU networks with the standard square loss, and show some of its improvements over the state-of-the-art. In particular, while prior works require all…

Machine Learning · Computer Science 2021-06-14 Quynh Nguyen

We consider the task of properly PAC learning decision trees with queries. Recent work of Koch, Strassle, and Tan showed that the strictest version of this task, where the hypothesis tree $T$ is required to be optimally small, is NP-hard.…

Computational Complexity · Computer Science 2024-07-02 Caleb Koch , Carmen Strassle , Li-Yang Tan

Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqrt{T}$-type regret in the unregularized setting. However, the…

Machine Learning · Computer Science 2026-03-03 Kaixuan Ji , Qingyue Zhao , Heyang Zhao , Qiwei Di , Quanquan Gu

We establish rigorous error bounds for prime counting using a truncated Gaussian (TG) kernel in the explicit formula framework. Our main theorem proves that the approximation error remains globally below 1/2 for all sufficiently large…

Number Theory · Mathematics 2025-07-01 Bugra Kilictas , Faruk Alpay

Fully-connected deep neural networks with weights initialized from independent Gaussian distributions can be tuned to criticality, which prevents the exponential growth or decay of signals propagating through the network. However, such…

Machine Learning · Computer Science 2024-06-13 Hannah Day , Yonatan Kahn , Daniel A. Roberts

Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ…

Computation and Language · Computer Science 2019-09-23 Alham Fikri Aji , Kenneth Heafield

Understanding the black-box prediction for neural networks is challenging. To achieve this, early studies have designed influence function (IF) to measure the effect of removing a single training point on neural networks. However, the…

Machine Learning · Computer Science 2023-11-27 Rui Zhang , Shihua Zhang

The Neural Tangent Kernel (NTK) framework has provided deep insights into the training dynamics of neural networks under gradient flow. However, it relies on the assumption that the network is differentiable with respect to its parameters,…

Machine Learning · Computer Science 2025-09-17 Sriram Nagaraj , Vishakh Hari

Recent studies on Neural Collapse (NC) reveal that, under class-balanced conditions, the class feature means and classifier weights spontaneously align into a simplex equiangular tight frame (ETF). In long-tailed regimes, however, severe…

Machine Learning · Computer Science 2025-12-10 Jinping Wang , Zhiqiang Gao , Zhiwu Xie

Period finding and phase estimation are fundamental in quantum computing. Prior work has established lower bounds on their success probabilities. Such quantum algorithms measure a state $|\hat\ell\rangle$ in an $n$-qubit computational…

Quantum Physics · Physics 2025-12-30 Malik Magdon-Ismail , Khai Dong

Quantization-aware training (QAT) is a leading technique for improving the accuracy of quantized neural networks. Previous work has shown that decomposing training into a full-precision (FP) phase followed by a QAT phase yields superior…

Machine Learning · Computer Science 2026-02-27 Aleksandr Dremov , David Grangier , Angelos Katharopoulos , Awni Hannun

Obtaining theoretical guarantees for neural networks training appears to be a hard problem in a general case. Recent research has been focused on studying this problem in the limit of infinite width and two different theories have been…

Machine Learning · Statistics 2020-10-27 Eugene A. Golikov

A quantum neural network (QNN) is a parameterized mapping efficiently implementable on near-term Noisy Intermediate-Scale Quantum (NISQ) computers. It can be used for supervised learning when combined with classical gradient-based…

Quantum Physics · Physics 2023-03-28 Xuchen You , Shouvanik Chakrabarti , Boyang Chen , Xiaodi Wu

Learning to differentiate model distributions from observed data is a fundamental problem in statistics and machine learning, and high-dimensional data remains a challenging setting for such problems. Metrics that quantify the disparity in…

Machine Learning · Statistics 2023-05-03 Matthew Repasky , Xiuyuan Cheng , Yao Xie

We prove tight lower bounds for the following variant of the counting problem considered by Aaronson, Kothari, Kretschmer, and Thaler (2020). The task is to distinguish whether an input set $x\subseteq [n]$ has size either $k$ or…

Quantum Physics · Physics 2024-05-08 Aleksandrs Belovs , Ansis Rosmanis

We introduce a scalable method to approximate the kernel of the Linearized Laplace Approximation (LLA). For this, we use a surrogate deep neural network (DNN) that learns a compact feature representation whose inner product replicates the…

Machine Learning · Computer Science 2026-02-04 Luis A. Ortega , Simón Rodríguez-Santana , Daniel Hernández-Lobato