Online learning: A comprehensive survey
Online learning represents a family of machine learning methods, where a learner attempts
to tackle some predictive (or any type of decision-making) task by learning from a sequence …
to tackle some predictive (or any type of decision-making) task by learning from a sequence …
Adaptive gradient-based meta-learning methods
We build a theoretical framework for designing and understanding practical meta-learning
methods that integrates sophisticated formalizations of task-similarity with the extensive …
methods that integrates sophisticated formalizations of task-similarity with the extensive …
A reduction of imitation learning and structured prediction to no-regret online learning
Sequential prediction problems such as imitation learning, where future observations
depend on previous predictions (actions), violate the common iid assumptions made in …
depend on previous predictions (actions), violate the common iid assumptions made in …
High probability convergence of stochastic gradient methods
In this work, we describe a generic approach to show convergence with high probability for
both stochastic convex and non-convex optimization with sub-Gaussian noise. In previous …
both stochastic convex and non-convex optimization with sub-Gaussian noise. In previous …
On the convergence of adaptive gradient methods for nonconvex optimization
[PDF][PDF] Composite objective mirror descent.
We present a new method for regularized convex optimization and analyze it under both
online and stochastic optimization settings. In addition to unifying previously known firstorder …
online and stochastic optimization settings. In addition to unifying previously known firstorder …