Add to ORKGThis paper presents competitive algorithms for a novel class of online optimization problems with memory. We consider a setting where the learner seeks to minimize the sum of a hitting cost and a switching cost that depends on the previous p decisions. This setting generalizes Smoothed Online Convex Optimization. The proposed approach, Optimistic Regularized Online Balanced Descent, achieves a constant, dimension-free competitive ratio. Further, we show a connection between online optimization with memory and online control with adversarial disturbances. This connection, in turn, leads to a new constant-competitive policy for a rich class of online control problems
The framework of online learning with memory naturally captures learning problems with temporal effe...
Making use of predictions is a crucial, but under-explored, area of online algorithms. This paper st...
International audienceWe consider the problem of online optimization, where a learner chooses a deci...
This paper presents competitive algorithms for a novel class of online optimization problems with me...
We consider Online Convex Optimization (OCO) in the setting where the costs are m-strongly convex an...
Recently a line of work has shown the applicability of tools from online optimization for control, l...
We consider Online Convex Optimization (OCO) in the setting where the costs are mm-strongly convex a...
We study Smoothed Online Convex Optimization, a version of online convex optimization where the lear...
We consider algorithms for "smoothed online convex optimization (SOCO)" problems. SOCO is a variant ...
We consider the fundamental problem of online control of a linear dynamical system from two differen...
We study online optimization in a setting where an online learner seeks to optimize a per-round hitt...
We study the performance of an online learner under a framework in which it receives partial informa...
We consider a natural online optimization problem set on the real line. The state of the online algo...
We examine the problem of smoothed online optimization, where a decision maker must sequentially cho...
In the last century, the problem of controlling a dynamical system has been a core component in nume...
The framework of online learning with memory naturally captures learning problems with temporal effe...
Making use of predictions is a crucial, but under-explored, area of online algorithms. This paper st...
International audienceWe consider the problem of online optimization, where a learner chooses a deci...
This paper presents competitive algorithms for a novel class of online optimization problems with me...
We consider Online Convex Optimization (OCO) in the setting where the costs are m-strongly convex an...
Recently a line of work has shown the applicability of tools from online optimization for control, l...
We consider Online Convex Optimization (OCO) in the setting where the costs are mm-strongly convex a...
We study Smoothed Online Convex Optimization, a version of online convex optimization where the lear...
We consider algorithms for "smoothed online convex optimization (SOCO)" problems. SOCO is a variant ...
We consider the fundamental problem of online control of a linear dynamical system from two differen...
We study online optimization in a setting where an online learner seeks to optimize a per-round hitt...
We study the performance of an online learner under a framework in which it receives partial informa...
We consider a natural online optimization problem set on the real line. The state of the online algo...
We examine the problem of smoothed online optimization, where a decision maker must sequentially cho...
In the last century, the problem of controlling a dynamical system has been a core component in nume...
The framework of online learning with memory naturally captures learning problems with temporal effe...
Making use of predictions is a crucial, but under-explored, area of online algorithms. This paper st...
International audienceWe consider the problem of online optimization, where a learner chooses a deci...