English
Related papers

Related papers: Normalized Square Root: Sharper Matrix Factorizati…

200 papers

We consider the differentially private (DP) facility location problem in the so called super-set output setting proposed by Gupta et al. [SODA 2010]. The current best known expected approximation ratio for an $\epsilon$-DP algorithm is…

Data Structures and Algorithms · Computer Science 2024-03-11 Pasin Manurangsi

Differential privacy has become a widely accepted notion of privacy, leading to the introduction and deployment of numerous privatization mechanisms. However, ensuring the privacy guarantee is an error-prone process, both in designing…

Information Theory · Computer Science 2019-05-27 Xiyang Liu , Sewoong Oh

Differentially Private Stochastic Gradient Descent (DP-SGD) is a cornerstone technique for ensuring privacy in deep learning, widely used in both training from scratch and fine-tuning large-scale language models. While DP-SGD predominantly…

Cryptography and Security · Computer Science 2026-03-10 Meisam Mohammady , Qin Yang , Nicholas Stout , Ayesha Samreen , Han Wang , Christopher J Quinn , Yuan Hong

Matrix factorization is a simple and natural test-bed to investigate the implicit regularization of gradient descent. Gunasekar et al. (2017) conjectured that Gradient Flow with infinitesimal initialization converges to the solution that…

Machine Learning · Computer Science 2021-04-13 Zhiyuan Li , Yuping Luo , Kaifeng Lyu

In order to provide a guaranteed precision and a more accurate judgement about the true value of the Cram\'{e}r-Rao bound and its scaling behavior, an upper bound (equivalently a lower bound on the quantum Fisher information) for precision…

Quantum Physics · Physics 2017-05-04 R. Yousefjani , S. Salimi , A. S. Khorashad

We show that convex-concave Lipschitz stochastic saddle point problems (also known as stochastic minimax optimization) can be solved under the constraint of $(\epsilon,\delta)$-differential privacy with \emph{strong (primal-dual) gap} rate…

Machine Learning · Computer Science 2023-06-30 Raef Bassily , Cristóbal Guzmán , Michael Menart

We present an algorithm to reduce the computational effort for the multiplication of a given matrix with an unknown column vector. The algorithm decomposes the given matrix into a product of matrices whose entries are either zero or integer…

Information Theory · Computer Science 2020-02-28 Ralf R. Müller , Bernhard Gäde , Ali Bereyhi

Leveraging algorithmic stability to derive sharp generalization bounds is a classic and powerful approach in learning theory. Since Vapnik and Chervonenkis [1974] first formalized the idea for analyzing SVMs, it has been utilized to study…

Machine Learning · Computer Science 2021-01-26 Qinghua Liu , Zhou Lu

Many applications require minimizing a family of optimization problems indexed by some hyperparameter $\lambda \in \Lambda$ to obtain an entire solution path. Traditional approaches proceed by discretizing $\Lambda$ and solving a series of…

Optimization and Control · Mathematics 2025-03-12 Qiran Dong , Paul Grigas , Vishal Gupta

The complexity of matrix multiplication is measured in terms of $\omega$, the smallest real number such that two $n\times n$ matrices can be multiplied using $O(n^{\omega+\epsilon})$ field operations for all $\epsilon>0$; the best bound…

Data Structures and Algorithms · Computer Science 2024-09-11 Josh Alman , Virginia Vassilevska Williams

We study the computational cost of differential privacy in terms of memory efficiency. While the trade-off between accuracy and differential privacy is well-understood, the inherent cost of privacy regarding memory use remains largely…

Cryptography and Security · Computer Science 2026-02-13 Alessandro Epasto , Xin Lyu , Pasin Manurangsi

Min-plus product of two $n\times n$ matrices is a fundamental problem in algorithm research. It is known to be equivalent to APSP, and in general it has no truly subcubic algorithms. In this paper, we focus on the min-plus product on a…

Data Structures and Algorithms · Computer Science 2022-02-03 Shucheng Chi , Ran Duan , Tianle Xie

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

Sequential querying of differentially private mechanisms degrades the overall privacy level. In this paper, we answer the fundamental question of characterizing the level of overall privacy degradation as a function of the number of queries…

Data Structures and Algorithms · Computer Science 2015-12-08 Peter Kairouz , Sewoong Oh , Pramod Viswanath

Achieving optimal statistical performance while ensuring the privacy of personal data is a challenging yet crucial objective in modern data analysis. However, characterizing the optimality, particularly the minimax lower bound, under…

Statistics Theory · Mathematics 2025-07-15 T. Tony Cai , Yichen Wang , Linjun Zhang

Cilleruelo conjectured that for an irreducible polynomial $f \in \mathbb{Z}[X]$ of degree $d \geq 2$, denoting $$L_f(N)=\mathrm{lcm}(f(1),f(2),\ldots f(N))$$ one has $$\log L_f(n)\sim(d-1)N\log N.$$ He proved it in the case $d=2$ but it…

Number Theory · Mathematics 2025-09-18 Alexei Entin

Weight decay is ubiquitous in training deep neural network architectures. Its empirical success is often attributed to capacity control; nonetheless, our theoretical understanding of its effect on the loss landscape and the set of…

Machine Learning · Statistics 2026-03-31 Anil Kamber , Rahul Parhi

A new line of work [Dwork et al. STOC 2015], [Hardt and Ullman FOCS 2014], [Steinke and Ullman COLT 2015], [Bassily et al. STOC 2016] demonstrates how differential privacy [Dwork et al. TCC 2006] can be used as a mathematical tool for…

Machine Learning · Computer Science 2017-03-07 Kobbi Nissim , Uri Stemmer

We propose differentially private algorithms for parameter estimation in both low-dimensional and high-dimensional sparse generalized linear models (GLMs) by constructing private versions of projected gradient descent. We show that the…

Machine Learning · Statistics 2020-12-08 T. Tony Cai , Yichen Wang , Linjun Zhang

We study differentially private (DP) training with Muon, a matrix-valued optimizer that updates hidden-layer weights using momentum followed by Newton--Schulz orthogonalization. While DP-SGD is well understood, the interaction between…

Machine Learning · Computer Science 2026-05-14 Jihwan Kim , Chenglin Fan