Sequential change-point detection when the distribution parameters are unknown is a fundamental problem in statistics and machine learning. When the post-change parameters are unknown, we consider a set of detection procedures based on sequential likelihood ratios with non-anticipating estimators constructed using online convex optimization algorithms such as online mirror descent, which provides a more versatile approach to tackling complex situations where recursive maximum likelihood estimators cannot be found. When the underlying distributions belong to a exponential family and the estimators satisfy the logarithm regret property, we show that this approach is nearly second-order asymptotically optimal. This means that the upper bound f...
Bandit convex optimization is a special case of online convex optimization with partial information....
Consider the online convex optimization problem, in which a player has to choose ac-tions iterativel...
The framework of online learning with memory naturally captures learning problems with temporal effe...
Sequential change-point detection when the distribution parameters are unknown is a fundamental prob...
International audienceIn this paper, we consider the problem of sequential change-point detection wh...
Abstract. This paper studies online change detection in exponential families when both the parameter...
This paper describes a methodology for detecting anomalies from sequentially observed and potentiall...
Abstract. This paper studies online change detection in exponential families when both the parameter...
International audienceThis paper studies online change detection in exponential families when both t...
AbstractShiryaev has obtained the optimal sequential rule for detecting the instant of a distributio...
In an online convex optimization problem a decision-maker makes a sequence of decisions, i.e., choos...
We study the parametric online changepoint detection problem, where the underlying distribution of t...
International audienceIn this paper, we consider the problem of sequential change-point detection wh...
We study the rates of growth of the regret in online convex optimization. First, we show that a simp...
In the sequential change-point detection literature, most research specifies a required frequency of...
Bandit convex optimization is a special case of online convex optimization with partial information....
Consider the online convex optimization problem, in which a player has to choose ac-tions iterativel...
The framework of online learning with memory naturally captures learning problems with temporal effe...
Sequential change-point detection when the distribution parameters are unknown is a fundamental prob...
International audienceIn this paper, we consider the problem of sequential change-point detection wh...
Abstract. This paper studies online change detection in exponential families when both the parameter...
This paper describes a methodology for detecting anomalies from sequentially observed and potentiall...
Abstract. This paper studies online change detection in exponential families when both the parameter...
International audienceThis paper studies online change detection in exponential families when both t...
AbstractShiryaev has obtained the optimal sequential rule for detecting the instant of a distributio...
In an online convex optimization problem a decision-maker makes a sequence of decisions, i.e., choos...
We study the parametric online changepoint detection problem, where the underlying distribution of t...
International audienceIn this paper, we consider the problem of sequential change-point detection wh...
We study the rates of growth of the regret in online convex optimization. First, we show that a simp...
In the sequential change-point detection literature, most research specifies a required frequency of...
Bandit convex optimization is a special case of online convex optimization with partial information....
Consider the online convex optimization problem, in which a player has to choose ac-tions iterativel...
The framework of online learning with memory naturally captures learning problems with temporal effe...