We present a novel approach to federated learning that endows its aggregation process with
greater robustness to potential poisoning of local data or model parameters of participating …

Weakly supervised object detection (WSOD) is a challenging task when provided with image
category supervision but required to simultaneously learn object locations and object …

Artificial intelligence has recently experienced remarkable advances, fueled by large
models, vast datasets, accelerated hardware, and, last but not least, the transformative …

This monograph is about a class of optimization algorithms called proximal algorithms. Much
like Newton's method is a standard tool for solving unconstrained smooth optimization …

A large number of attacks are launched daily in the era of the internet and with a large
number of users. Nowadays, effective detection of numerous attacks using the Intrusion …

Algorithmic stability is a classical approach to understanding and analysis of the
generalization error of learning algorithms. A notable weakness of most stability-based …

Dynamic path planning has gained increasing popularity in mobile robot navigation. Some
of the current path planning methods require a priori information about the motion space and …

We consider global efficiency of algorithms for minimizing a sum of a convex function and a
composition of a Lipschitz convex function with a smooth map. The basic algorithm we rely …

We discuss the foundational role of the proximal framework in the development and analysis
of some iconic first order optimization algorithms, with a focus on non-Euclidean proximal …

In this paper, we study a novel and widely existing problem in graph matching (GM), namely,
Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence …