Class-incremental learning (CIL) aims to train a classification model while the number of
classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity …

This text presents an introduction to an emerging paradigm in control of dynamical systems
and differentiable reinforcement learning called online nonstochastic control. The new …

As we move towards safety-critical cyber-physical systems that operate in non-stationary
and uncertain environments, it becomes crucial to close the gap between classical optimal …

Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL)
when the model continuously adapts to new classes. A common technique to address this is …

This paper considers online switching control with a finite candidate controller pool, an
unknown dynamical system, and unknown cost functions. The candidate controllers can be …

We study the adaptive control of an unknown linear system with a quadratic cost function
subject to safety constraints on both the states and actions. The challenges of this problem …

We study online adaptive policy selection in systems with time-varying costs and dynamics.
We develop the Gradient-based Adaptive Policy Selection (GAPS) algorithm together with a …

We propose an algorithm based on online convex optimization for controlling discrete-time
linear dynamical systems. The algorithm is data-driven, ie, does not require a model of the …

Projection operations are a typical computation bottleneck in online learning. In this paper,
we enable projection-free online learning within the framework of Online Convex …

We consider online convex optimization with time-varying stage costs and additional
switching costs. Since the switching costs introduce coupling across all stages, multi-step …