Adaptive Learning in a World of Projections

233 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Ideal Continual Learner: An Agent That Never Forgets (2023, methodology): “We refer the reader to Borwein & Tam (2014) for some equivalence among these methods and to Theodoridis et al. (2010); Lindstrom & Sims (2021) and some references of Borwein & Tam (2014) for surveys.”
Multitask Diffusion Adaptation Over Networks (2013, unknown): “All vectors are column vectors.”
Diffusion Adaptation Strategies for Distributed Optimization and Learning Over Networks (2011, background): “Therefore, in steady-state, we have lim i→∞ Ew̃i = 0 (94) Next, we determine an expression (rather than a bound) for the MSE.”
Wavefit: an Iterative and Non-Autoregressive Neural Vocoder Based on Fixed-Point Iteration (2022, methodology): “Since fixedpoint theory is a key tool for deterministic analysis of optimization and adaptive filter algorithms [65], WaveFit can be considered as an optimization-based or adaptive-filter-based neural vocoder.”
Robust Distributed Estimation by Networked Agents (2017, methodology): “In [16], a robust diffusion estimation algorithm is realized by using the adaptive projected subgradient method [17], [18], culminating in a combine-project-adapt protocol, where the output errors at each node are projected onto halfspaces defined by Huber’s M-estimate error function [19].”
A survey of machine learning for big data processing (2016, background): “online classification [66], convexly constrained parameter/function estimation [67], beamforming”