Overview
Making Non-Stochastic Control (Almost) as Easy as Stochastic
Recent literature has made much progress in understanding online LQR: a modern learning-theoretic take on the classical control problem where a learner attempts to optimally control an unknown linear dynamical system with fully observed state, perturbed by i.i.d.
GlanceNets: Interpretable, Leak-proof Concept-based Models
A key requirement is that the concepts be interpretable. Existing CBMs tackle this desideratum using a variety of heuristics based on unclear notions of interpretability, and fail to acquire concepts with the intended semantics.
Appendix A Review of Local Stability Results We provide a brief review of standard definitions and stability results that we use in the theorem
All the material can be found in any text in nonlinear systems such as [28]. That is, the system can remain arbitrarily close to the equilibrium point if it starts sufficiently close.
Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity
While our presentation focuses on this finite-sum structure, most of our convergence results can easily be adapted to the general stochastic setting (see App. D).
