English
Related papers

Related papers: f-divergences and their applications in lossy comp…

200 papers

We show that running gradient descent with variable learning rate guarantees loss $f(x) \leq 1.1 \cdot f(x^*) + \epsilon$ for the logistic regression objective, where the error $\epsilon$ decays exponentially with the number of iterations…

Machine Learning · Computer Science 2023-06-27 Kyriakos Axiotis , Maxim Sviridenko

This paper considers the problem of lossy compression for the computation of a function of two correlated sources, both of which are observed at the encoder. Due to presence of observation costs, the encoder is allowed to observe only…

Information Theory · Computer Science 2013-07-22 Xi Liu , Osvaldo Simeone , Elza Erkip

For solving constrained (pseudo)-monotone variational inequality, we prove that the upper bound of stepsize $\frac{1}{2L}$ established for the Popov's algorithm and the forward-reflected-backward algorithm is tight. For unconstrained case,…

Optimization and Control · Mathematics 2026-03-09 Nhung Hong Nguyen , Thanh Quoc Trinh , Phan Tu Vuong

We provide a detailed study on the implicit bias of gradient descent when optimizing loss functions with strictly monotone tails, such as the logistic loss, over separable datasets. We look at two basic questions: (a) what are the…

We analyse the convergence of an approximate, fully inexact, ADMM algorithm under additive, deterministic and probabilistic error models. We consider the generalized ADMM scheme that is derived from generalized Lagrangian penalty with…

Optimization and Control · Mathematics 2022-10-06 Anis Hamadouche , Yun Wu , Andrew M. Wallace , Joao F. C. Mota

In this paper we propose distributed dual gradient algorithms for linearly constrained separable convex problems and analyze their rate of convergence under different assumptions. Under the strong convexity assumption on the primal…

Optimization and Control · Mathematics 2014-02-04 Ion Necoara , Valentin Nedelcu

In this monograph, we review recent advances in second-order asymptotics for lossy source coding, which provides approximations to the finite blocklength performance of optimal codes. The monograph is divided into three parts. In part I, we…

Information Theory · Computer Science 2024-10-25 Lin Zhou , Mehul Motani

In probability theory, the Chernoff bound gives exponentially decreasing bounds on tail distributions for sums of independent random variables and such bound is applied at different fields in science and engineering. In this work, we…

Probability · Mathematics 2021-09-29 Shih Yu Chang

Lower bounds for the average probability of error of estimating a hidden variable X given an observation of a correlated random variable Y, and Fano's inequality in particular, play a central role in information theory. In this paper, we…

Information Theory · Computer Science 2013-10-08 Flavio du Pin Calmon , Mayank Varia , Muriel Médard , Mark M. Christiansen , Ken R. Duffy , Stefano Tessaro

In high-dimensional statistical inference, sparsity regularizations have shown advantages in consistency and convergence rates for coefficient estimation. We consider a generalized version of Sparse-Group Lasso which captures both…

Machine Learning · Statistics 2020-08-12 Xinyu Zhang

Often in the analysis of first-order methods for both smooth and nonsmooth optimization, assuming the existence of a growth/error bound or KL condition facilitates much stronger convergence analysis. Hence separate analysis is typically…

Optimization and Control · Mathematics 2023-01-10 Benjamin Grimmer

Transformers achieve superior performance on many tasks, but impose heavy compute and memory requirements during inference. This inference can be made more efficient by partitioning the process across multiple devices, which, in turn,…

Machine Learning · Computer Science 2026-04-21 Anderson de Andrade , Alon Harell , Ivan V. Bajić

The problem of variable-rate lossless data compression is considered, for codes with and without prefix constraints. Sharp bounds are derived for the best achievable compression rate of memoryless sources, when the excess-rate probability…

Information Theory · Computer Science 2025-11-13 Andreas Theocharous , Lampros Gavalakis , Ioannis Kontoyiannis

We examine the privacy amplification of channels that do not necessarily satisfy any LDP guarantee by analyzing their contraction behavior in terms of $f_\alpha$-divergence, an $f$-divergence related to R\'enyi-divergence via a monotonic…

Information Theory · Computer Science 2025-11-27 Leonhard Grosse , Sara Saeidian , Tobias J. Oechtering , Mikael Skoglund

The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled "Federated Learning with Formal Differential Privacy Guarantees"). In…

Machine Learning · Computer Science 2024-02-06 Monika Henzinger , Jalaj Upadhyay , Sarvagya Upadhyay

In this paper we derive information theoretic performance bounds to sensing and reconstruction of sparse phenomena from noisy projections. We consider two settings: output noise models where the noise enters after the projection and input…

Information Theory · Computer Science 2011-12-22 Shuchin Aeron , Venkatesh Saligrama , Manqi Zhao

In this paper we analyze the joint rate distortion function (RDF), for a tuple of correlated sources taking values in abstract alphabet spaces (i.e., continuous) subject to two individual distortion criteria. First, we derive structural…

Information Theory · Computer Science 2021-05-11 Evagoras Stylianou , Charalambos D. Charalambous , Themistoklis Charalambous

Generalization error bounds for deep neural networks trained by stochastic gradient descent (SGD) are derived by combining a dynamical control of an appropriate parameter norm and the Rademacher complexity estimate based on parameter norms.…

Machine Learning · Computer Science 2023-05-30 Mingze Wang , Chao Ma

We consider optimization of generalized performance metrics for binary classification by means of surrogate losses. We focus on a class of metrics, which are linear-fractional functions of the false positive and false negative rates…

Machine Learning · Computer Science 2016-10-10 Wojciech Kotłowski , Krzysztof Dembczyński

We introduce a two-parameter family of discrepancy measures, termed \emph{$(G,f)$-divergences}, obtained by applying a non-decreasing function $G$ to an $f$-divergence $D_f$. Building on Csisz\'ar's formulation of mutual $f$-information, we…

Information Theory · Computer Science 2026-01-23 Hamidreza Abin , Mahdi Zinati , Amin Gohari , Mohammad Hossein Yassaee , Mohammad Mahdi Mojahedian