Edge computing is a paradigm that shifts data processing services to the network edge,
where data are generated. While such an architecture provides faster processing and …

Many settings involve sequential decision making where a set of actions can be chosen at
each time step, each action provides a stochastic reward, and the distribution for the reward …

This article addresses the application of minimax optimization in the control design of
complex dynamic systems of the semiconductor manufacturing. We highlight the main …

We consider a linear regression game in which the covariates are known in advance: at
each round, the learner predicts a real-value, the adversary reveals a label, and the learner …

We consider an adversarial formulation of the problem ofpredicting a time series with square
loss. The aim is to predictan arbitrary sequence of vectors almost as well as the bestsmooth …

We analyze the convergence rates of stochastic gradient algorithms for smooth finite-sum
minimax optimization and show that, for many such algorithms, sampling the data …

We consider online linear regression: at each round, an adversary reveals a covariate
vector, the learner predicts a real value, the adversary reveals a label, and the learner …

We develop a new theoretical framework, the envelope complexity, to analyze the minimax
regret with logarithmic loss functions. Within the framework, we derive a Bayesian predictor …

Much of the work in online learning focuses on the study of sublinear upper bounds on the
regret. In this work, we initiate the study of best-case lower bounds in online convex …

We consider the online prediction of a varying Bernoulli process (sequence of varying
Bernoulli probabilities) from a single binary sequence. A real-valued online prediction …