English
Related papers

Related papers: Conspiracies between Learning Algorithms, Circuit …

200 papers

Consider the problem of learning the drift coefficient of a stochastic differential equation from a sample path. In this paper, we assume that the drift is parametrized by a high dimensional vector. We address the question of how long the…

Information Theory · Computer Science 2011-03-10 José Bento , Morteza Ibrahimi , Andrea Montanari

Sensitivity measures how much the output of an algorithm changes, in terms of Hamming distance, when part of the input is modified. While approximation algorithms with low sensitivity have been developed for many problems, no sensitivity…

Data Structures and Algorithms · Computer Science 2025-10-17 Noah Fleming , Yuichi Yoshida

This work investigates the ``small-vs-large gap'', where repeating on fewer samples can lead to compute saving during training compared to using a larger dataset. This is observed across algorithmic tasks, architectures and optimizers and…

Machine Learning · Computer Science 2026-05-21 Jingwen Liu , Ezra Edelman , Surbhi Goel , Bingbin Liu

Closed-loop learning is the process of repeatedly estimating a model from data generated from the model itself. It is receiving great attention due to the possibility that large neural network models may, in the future, be primarily trained…

Machine Learning · Computer Science 2025-07-10 Fariba Jangjoo , Matteo Marsili , Yasser Roudi

Learned index structures aim to accelerate queries by training machine learning models to approximate the rank function associated with a database attribute. While effective in practice, their theoretical limitations are not fully…

Data Structures and Algorithms · Computer Science 2026-01-13 Luis Alberto Croquevielle , Roman Sokolovskii , Thomas Heinis

Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-labels for the unlabeled examples and progressively refines…

Machine Learning · Computer Science 2020-06-22 Samet Oymak , Talha Cihad Gulcu

Learning-based low rank approximation algorithms can significantly improve the performance of randomized low rank approximation with sketch matrix. With the learned value and fixed non-zero positions for sketch matrices from learning-based…

Machine Learning · Computer Science 2022-12-19 Tiejin Chen , Yicheng Tao

Probabilistic logical models are a core component of neurosymbolic AI and are important in their own right for tasks that require high explainability. Unlike neural networks, logical theories that underlie the model are often handcrafted…

Artificial Intelligence · Computer Science 2025-10-07 Jonathan Feldstein , Dominic Phillips , Efthymia Tsamoura

We develop a pseudo-likelihood theory for rank one matrix estimation problems in the high dimensional limit. We prove a variational principle for the limiting pseudo-maximum likelihood which also characterizes the performance of the…

Statistics Theory · Mathematics 2025-11-10 Curtis Grant , Aukosh Jagannath , Justin Ko

We investigate three related and important problems connected to machine learning: approximating a submodular function everywhere, learning a submodular function (in a PAC-like setting [53]), and constrained minimization of submodular…

Data Structures and Algorithms · Computer Science 2013-11-12 Rishabh Iyer , Stefanie Jegelka , Jeff Bilmes

A recent work (Korten, Pitassi, and Impagliazzo, FOCS 2025) established an insightful connection between static data structure lower bounds, range avoidance of $\text{NC}^0$ circuits, and the refutation of pseudorandom CSP instances,…

Computational Complexity · Computer Science 2025-07-31 Venkatesan Guruswami , Xin Lyu , Weiqiang Yuan

Recent research demonstrated that training large language models involves memorization of a significant fraction of training data. Such memorization can lead to privacy violations when training on sensitive user data and thus motivates the…

Machine Learning · Computer Science 2025-10-29 Vitaly Feldman , Guy Kornowski , Xin Lyu

Neural network models have achieved high performance on a wide variety of complex tasks, but the algorithms that they implement are notoriously difficult to interpret. It is often necessary to hypothesize intermediate variables involved in…

Computation and Language · Computer Science 2025-02-13 Michael A. Lepori , Thomas Serre , Ellie Pavlick

We connect the study of pseudodeterministic algorithms to two major open problems about the structural complexity of $\mathsf{BPTIME}$: proving hierarchy theorems and showing the existence of complete problems. Our main contributions can be…

Computational Complexity · Computer Science 2021-03-16 Zhenjian Lu , Igor C. Oliveira , Rahul Santhanam

We use entropy numbers in combination with the polynomial method to derive a new general lower bound for the n-th minimal error in the quantum setting of information-based complexity. As an application, we improve some lower bounds on…

Quantum Physics · Physics 2007-05-23 Stefan Heinrich

The iterations of many first-order algorithms, when applied to minimizing common regularized regression functions, often resemble neural network layers with pre-specified weights. This observation has prompted the development of…

Machine Learning · Computer Science 2017-08-03 Hao He , Bo Xin , David Wipf

This paper deals with a class of neural SDEs and studies the limiting behavior of the associated sampled optimal control problems as the sample size grows to infinity. The neural SDEs with $N$ samples can be linked to the $N$-particle…

Optimization and Control · Mathematics 2025-06-19 Huafu Liao , Alpár R. Mészáros , Chenchen Mou , Chao Zhou

In this paper, we study gap-dependent regret guarantees for risk-sensitive reinforcement learning based on the entropic risk measure. We propose a novel definition of sub-optimality gaps, which we call cascaded gaps, and we discuss their…

Machine Learning · Computer Science 2022-03-08 Yingjie Fei , Ruitu Xu

The AWGNC, BSC, and max-fractional pseudocodeword redundancies of a binary linear code are defined to be the smallest number of rows in a parity-check matrix such that the corresponding minimum pseudoweight is equal to the minimum Hamming…

Information Theory · Computer Science 2012-03-07 Jens Zumbrägel , Vitaly Skachek , Mark F. Flanagan

This paper argues that the judicial use of formal language theory and grammatical inference are invaluable tools in understanding how deep neural networks can and cannot represent and learn long-term dependencies in temporal sequences.…

Computation and Language · Computer Science 2017-10-17 Enes Avcu , Chihiro Shibata , Jeffrey Heinz