English
Related papers

Related papers: Generalized Random Gilbert-Varshamov Codes: Typica…

200 papers

We consider the optimization of a smooth and strongly convex objective using constant step-size stochastic gradient descent (SGD) and study its properties through the prism of Markov chains. We show that, for unbiased gradient estimates…

Machine Learning · Statistics 2025-11-25 Ibrahim Merad , Stéphane Gaïffas

We establish in-expectation and tail bounds on the generalization error of representation learning type algorithms. The bounds are in terms of the relative entropy between the distribution of the representations extracted from the training…

Machine Learning · Statistics 2025-03-21 Milad Sefidgaran , Abdellatif Zaidi , Piotr Krasnowski

We consider a broadcast channel with a degraded message set, in which a single transmitter sends a common message to two receivers and a private message to one of the receivers only. The main goal of this work is to find new lower bounds to…

Information Theory · Computer Science 2009-06-09 Yonatan Kaspi , Neri Merhav

This paper presents generalized channel coding theorems for a time-slotted distributed communication system where a transmitter-receiver pair is communicating in parallel with other transmitters. Assume that the channel code of each…

Information Theory · Computer Science 2016-11-15 Jie Luo

Region-of-Interest (ROI)-based image compression allocates bits unevenly according to the semantic importance of different regions. Such differentiated coding typically induces a sharp-peaked and heavy-tailed distribution. This distribution…

Image and Video Processing · Electrical Eng. & Systems 2026-02-03 Kai Hu , Junfu Tan , Fang Xu , Ramy Samy , Yu Liu

In this paper we provide explicit upper bounds on some distances between the (law of the) output of a random Gaussian NN and (the law of) a random Gaussian vector. Our results concern both shallow random Gaussian neural networks with…

We study generalization properties of random features (RF) regression in high dimensions optimized by stochastic gradient descent (SGD) in under-/over-parameterized regime. In this work, we derive precise non-asymptotic error bounds of RF…

Machine Learning · Statistics 2022-10-18 Fanghui Liu , Johan A. K. Suykens , Volkan Cevher

We consider a decoder with an erasure option and a variable size list decoder for channels with non-casual side information at the transmitter. First, universally achievable error exponents are offered for decoding with an erasure option…

Information Theory · Computer Science 2009-03-13 Erez Sabbag , Neri Merhav

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

The Randomized Singular Value Decomposition (RSVD) is a widely used algorithm for efficiently computing low-rank approximations of large matrices, without the need to construct a full-blown SVD. Of interest, of course, is the approximation…

Numerical Analysis · Mathematics 2025-10-09 Danil Akhtiamov , Reza Ghane , Babak Hassibi

We study variable-length feedback (VLF) codes with noiseless feedback for discrete memoryless channels. We present a novel non-asymptotic bound, which analyzes the average error probability and average decoding time of our modified…

Information Theory · Computer Science 2025-02-12 Recep Can Yavas , Vincent Y. F. Tan

In this work, we derive the random coding error exponent for the uplink phase of a two-way relay system where physical layer network coding (PNC) is employed. The error exponent is derived for the practical (yet sub-optimum) XOR channel…

Information Theory · Computer Science 2017-02-07 Shakeel Salamat Ullah , Gianluigi Liva , Soung Chang Liew

We determine the exact error and strong converse exponents of shared randomness-assisted channel simulation in worst case total-variation distance. Namely, we find that these exponents can be written as simple optimizations over the R\'enyi…

Information Theory · Computer Science 2024-10-10 Aadil Oufkir , Michael X. Cao , Hao-Chung Cheng , Mario Berta

Consider a lossy compression system with $\ell$ distributed encoders and a centralized decoder. Each encoder compresses its observed source and forwards the compressed data to the decoder for joint reconstruction of the target signals under…

Information Theory · Computer Science 2018-07-19 Yizhong Wang , Li Xie , Xuan Zhang , Jun Chen

We derive the optimum second-order coding rates, known as second-order capacities, for erasure and list decoding. For erasure decoding for discrete memoryless channels, we show that second-order capacity is $\sqrt{V}\Phi^{-1}(\epsilon_t)$…

Information Theory · Computer Science 2014-04-22 Vincent Y. F. Tan , Pierre Moulin

We analyze prediction error in stochastic dynamical systems with memory, focusing on generalized Langevin equations (GLEs) formulated as stochastic Volterra equations. We establish that, under a strongly convex potential, trajectory…

Machine Learning · Statistics 2025-12-12 Quanjun Lang , Jianfeng Lu

We derive a general formula of the minimum achievable rate for fixed-to-variable length coding with a regular cost function by allowing the error probability up to a constant $\varepsilon$. For a fixed-to-variable length code, we call the…

Information Theory · Computer Science 2017-10-11 Hideki Yagi , Ryo Nomura

When computing systems can tolerate the effects of errors or erasures in their communicated data values, they can trade this tolerance for improved resource efficiency. One method for enabling this tradeoff in the I/O subsystems of…

Information Theory · Computer Science 2018-09-18 Phillip Stanley-Marbell , Paul Hurley

This paper concerns itself with the question of list decoding for general adversarial channels, e.g., bit-flip ($\textsf{XOR}$) channels, erasure channels, $\textsf{AND}$ ($Z$-) channels, $\textsf{OR}$ channels, real adder channels, noisy…

Information Theory · Computer Science 2019-09-11 Yihan Zhang , Amitalok J. Budkuley , Sidharth Jaggi

Symbolic regression (SR) with genetic programming (GP) aims to discover interpretable mathematical expressions directly from data. Despite its strong empirical success, the theoretical understanding of why GP-based SR generalizes beyond the…

Machine Learning · Computer Science 2026-04-21 Masahiro Nomura , Ryoki Hamano , Isao Ono