English
Related papers

Related papers: Finite Littlestone Dimension Implies Finite Inform…

200 papers

We provide a full characterization of the concept classes that are optimistically universally online learnable with $\{0, 1\}$ labels. The notion of optimistically universal online learning was defined in [Hanneke, 2021] in order to…

Machine Learning · Statistics 2025-01-16 Steve Hanneke , Hongao Wang

In this work, we study online submodular maximization, and how the requirement of maintaining a stable solution impacts the approximation. In particular, we seek bounds on the best-possible approximation ratio that is attainable when the…

Data Structures and Algorithms · Computer Science 2024-12-04 Paul Dütting , Federico Fusco , Silvio Lattanzi , Ashkan Norouzi-Fard , Ola Svensson , Morteza Zadimoghaddam

We study the online learnability of hypothesis classes with respect to arbitrary, but bounded loss functions. No characterization of online learnability is known at this level of generality. We give a new scale-sensitive combinatorial…

Machine Learning · Computer Science 2024-02-12 Vinod Raman , Unique Subedi , Ambuj Tewari

The stunning empirical successes of neural networks currently lack rigorous theoretical explanation. What form would such an explanation take, in the face of existing complexity-theoretic lower bounds? A first step might be to show that…

Machine Learning · Computer Science 2017-07-18 Le Song , Santosh Vempala , John Wilmes , Bo Xie

We present the first nearly optimal differentially private PAC learner for any concept class with VC dimension 1 and Littlestone dimension $d$. Our algorithm achieves the sample complexity of…

Machine Learning · Computer Science 2025-07-30 Chao Yan

Let $\mathscr{F}_{n,d}$ be the class of all functions $f:\{-1,1\}^n\to[-1,1]$ on the $n$-dimensional discrete hypercube of degree at most $d$. In the first part of this paper, we prove that any (deterministic or randomized) algorithm which…

Machine Learning · Computer Science 2024-10-23 Alexandros Eskenazis , Paata Ivanisvili , Lauritz Streck

Previous work has shown that DNNs with large depth $L$ and $L_{2}$-regularization are biased towards learning low-dimensional representations of the inputs, which can be interpreted as minimizing a notion of rank $R^{(0)}(f)$ of the learned…

Machine Learning · Computer Science 2024-08-16 Arthur Jacot

This paper presents the thesis that all learning agents of finite information size are limited by their informational structure in what goals they can efficiently learn to achieve in a complex environment. Evolutionary change is critical…

Artificial Intelligence · Computer Science 2013-04-03 Alok Raj

Information theory provides tools to predict the performance of a learning algorithm on a given dataset. For instance, the accuracy of learning an unknown parameter can be upper bounded by reducing the learning task to hypothesis testing…

Quantum Physics · Physics 2026-04-21 Evan Peters

We study universal consistency of non-i.i.d. processes in the context of online learning. A stochastic process is said to admit universal consistency if there exists a learner that achieves vanishing average loss for any measurable response…

Machine Learning · Computer Science 2022-07-19 Moïse Blanchard , Romain Cosson

We initiate a study of algorithms with a focus on the computational complexity of individual elements, and introduce the fragile complexity of comparison-based algorithms as the maximal number of comparisons any individual element takes…

Data Structures and Algorithms · Computer Science 2019-09-04 Peyman Afshani , Rolf Fagerberg , David Hammer , Riko Jacob , Irina Kostitsyna , Ulrich Meyer , Manuel Penschuck , Nodari Sitchinava

Deep neural networks (DNNs) have shown great success in many machine learning tasks. Their training is challenging since the loss surface of the network architecture is generally non-convex, or even non-smooth. How and under what…

Machine Learning · Computer Science 2022-02-09 Lam M. Nguyen , Trang H. Tran , Marten van Dijk

Complexity of patterns is a key information for human brain to differ objects of about the same size and shape. Like other innate human senses, the complexity perception cannot be easily quantified. We propose a transparent and universal…

Pattern Formation and Solitons · Physics 2020-12-30 Andrey A. Bagrov , Ilia A. Iakovlev , Askar A. Iliasov , Mikhail I. Katsnelson , Vladimir V. Mazurenko

Robust estimation is much more challenging in high dimensions than it is in one dimension: Most techniques either lead to intractable optimization problems or estimators that can tolerate only a tiny fraction of errors. Recent work in…

Machine Learning · Computer Science 2018-03-14 Ilias Diakonikolas , Gautam Kamath , Daniel M. Kane , Jerry Li , Ankur Moitra , Alistair Stewart

In this paper we describe an algorithm for the computation of canonical forms of finite subsets of $\mathbb{Z}^d$, up to affinities over $\mathbb{Z}$. For fixed dimension $d$, this algorithm has worst-case asymptotic complexity $O(n \log^2…

Data Structures and Algorithms · Computer Science 2018-09-28 Giovanni Paolini

The minimization of convex functions which are only available through partial and noisy information is a key methodological problem in many disciplines. In this paper we consider convex optimization with noisy zero-th order information,…

Machine Learning · Computer Science 2016-05-27 Francis Bach , Vianney Perchet

In lifelong learning, tasks (or classes) to be learned arrive sequentially over time in arbitrary order. During training, knowledge from previous tasks can be captured and transferred to subsequent ones to improve sample efficiency. We…

Machine Learning · Computer Science 2022-03-02 Xinyuan Cao , Weiyang Liu , Santosh S. Vempala

Effective complexity measures the information content of the regularities of an object. It has been introduced by M. Gell-Mann and S. Lloyd to avoid some of the disadvantages of Kolmogorov complexity, also known as algorithmic information…

Information Theory · Computer Science 2010-11-22 Nihat Ay , Markus Mueller , Arleta Szkola

In this paper, we study the online learning algorithm without explicit regularization terms. This algorithm is essentially a stochastic gradient descent scheme in a reproducing kernel Hilbert space (RKHS). The polynomially decaying step…

Machine Learning · Computer Science 2017-10-11 Zheng-Chu Guo , Lei Shi

We study the finite-step realizability of the joint/generalized spectral radius of a pair of real $d\times d$ matrices, one of which has rank 1. Then we prove that there always exists a finite-length word for which there holds the spectral…

Optimization and Control · Mathematics 2011-06-07 Xiongping Dai