English
Related papers

Related papers: Gradient Descent is Pareto-Optimal in the Oracle C…

200 papers

Consider an oracle which takes a point $x$ and returns the minimizer of a convex function $f$ in an $\ell_2$ ball of radius $r$ around $x$. It is straightforward to show that roughly $r^{-1}\log\frac{1}{\epsilon}$ calls to the oracle…

Optimization and Control · Mathematics 2020-03-19 Yair Carmon , Arun Jambulapati , Qijia Jiang , Yujia Jin , Yin Tat Lee , Aaron Sidford , Kevin Tian

Gradient descent and its variants are widely used in machine learning. However, oracle access of gradient may not be available in many applications, limiting the direct use of gradient descent. This paper proposes a method of estimating…

Optimization and Control · Mathematics 2019-10-07 Qinbo Bai , Mridul Agarwal , Vaneet Aggarwal

This paper is devoted to the study of stochastic optimization problems under the generalized smoothness assumption. By considering the unbiased gradient oracle in Stochastic Gradient Descent, we provide strategies to achieve in bounds the…

Optimization and Control · Mathematics 2025-05-26 Aleksandr Lobanov , Alexander Gasnikov

When designing an algorithm, one cares about arithmetic/computational complexity, but data movement (I/O) complexity plays an increasingly important role that highly impacts performance and energy consumption. For a given algorithm and a…

Computational Complexity · Computer Science 2024-04-26 Lionel Eyraud-Dubois , Guillaume Iooss , Julien Langou , Fabrice Rastello

Stochastic Gradient (SG) is the defacto iterative technique to solve stochastic optimization (SO) problems with a smooth (non-convex) objective $f$ and a stochastic first-order oracle. SG's attractiveness is due in part to its simplicity of…

Optimization and Control · Mathematics 2024-03-08 David Newton , Raghu Bollapragada , Raghu Pasupathy , Nung Kwan Yip

We introduce the Optimizing a Discrete Loss (ODIL) framework for the numerical solution of Partial Differential Equations (PDE) using machine learning tools. The framework formulates numerical methods as a minimization of discrete residuals…

Numerical Analysis · Mathematics 2024-01-23 Petr Karnakov , Sergey Litvinov , Petros Koumoutsakos

This paper studies the complexity of projected gradient descent methods for a class of strongly convex constrained optimization problems where the objective function is expressed as a summation of $m$ component functions, each possessing a…

Optimization and Control · Mathematics 2026-02-10 Xiaojun Chen , C. T. Kelley , Lei Wang

Optimization problems in disciplines such as machine learning are commonly solved with iterative methods. Gradient descent algorithms find local minima by moving along the direction of steepest descent while Newton's method takes into…

Quantum Physics · Physics 2018-08-20 Patrick Rebentrost , Maria Schuld , Leonard Wossnig , Francesco Petruccione , Seth Lloyd

Several recent empirical studies demonstrate that important machine learning tasks, e.g., training deep neural networks, exhibit low-rank structure, where the loss function varies significantly in only a few directions of the input space.…

Machine Learning · Computer Science 2022-06-17 Romain Cosson , Ali Jadbabaie , Anuran Makur , Amirhossein Reisizadeh , Devavrat Shah

We study the query complexity of min-max optimization of a nonconvex-nonconcave function $f$ over $[0,1]^d \times [0,1]^d$. We show that, given oracle access to $f$ and to its gradient $\nabla f$, any algorithm that finds an…

Data Structures and Algorithms · Computer Science 2026-05-14 Martino Bernasconi , Matteo Castiglioni , Andrea Celli , Alexandros Hollender

We present differentially private (DP) algorithms for bilevel optimization, a problem class that received significant attention lately in various machine learning applications. These are the first algorithms for such problems under standard…

Machine Learning · Computer Science 2026-01-15 Guy Kornowski

We propose an extragradient method with stepsizes bounded away from zero for stochastic variational inequalities requiring only pseudo-monotonicity. We provide convergence and complexity analysis, allowing for an unbounded feasible set,…

Optimization and Control · Mathematics 2017-03-02 Alfredo Iusem , Alejandro Jofré , Roberto I. Oliveira , Philip Thompson

The performance of stochastic gradient descent (SGD), which is the simplest first-order optimizer for training deep neural networks, depends on not only the learning rate but also the batch size. They both affect the number of iterations…

Machine Learning · Statistics 2024-02-26 Kento Imaizumi , Hideaki Iiduka

Learning rates in stochastic neural network training are currently determined a priori to training, using expensive manual or automated iterative tuning. This study proposes gradient-only line searches to resolve the learning rate for…

Machine Learning · Statistics 2020-01-16 Dominic Kafka , Daniel N. Wilke

We initiate a systematic study of pseudo-deterministic quantum algorithms. These are quantum algorithms that, for any input, output a canonical solution with high probability. Focusing on the query complexity model, our main contributions…

Quantum Physics · Physics 2026-02-20 Hugo Aaronson , Tom Gur , Jiawei Li

Although nearly 20 years have passed since its conception, the feasibility pump algorithm remains a widely used heuristic to find feasible primal solutions to mixed-integer linear problems. Many extensions of the initial algorithm have been…

Optimization and Control · Mathematics 2024-11-07 Matteo Cacciola , Alexandre Forel , Antonio Frangioni , Andrea Lodi

Linear programming (LP) relaxation is a standard technique for solving hard combinatorial optimization (CO) problems. Here we present a gradient descent algorithm which exploits the special structure of some LP relaxations induced by CO…

Optimization and Control · Mathematics 2020-11-17 Alexey Antonov

We consider the problem of simultaneously learning to linearly combine a very large number of kernels and learn a good predictor based on the learnt kernel. When the number of kernels $d$ to be combined is very large, multiple kernel…

Machine Learning · Computer Science 2015-03-20 Arash Afkanpour , András György , Csaba Szepesvári , Michael Bowling

ADAGB2, a generalization of the Adagrad algorithm for stochastic optimization is introduced, which is also applicable to bound-constrained problems and capable of using second-order information when available. It is shown that, given…

Optimization and Control · Mathematics 2025-05-13 S. Bellavia , S. Gratton , B. Morini , Ph. L. Toint

We show a new lower bound on the sample complexity of $(\varepsilon, \delta)$-differentially private algorithms that accurately answer statistical queries on high-dimensional databases. The novelty of our bound is that it depends optimally…

Data Structures and Algorithms · Computer Science 2015-01-27 Thomas Steinke , Jonathan Ullman