Incremental Learning in Mirror Flows
We study mirror flows generated by a convex quadratic loss and a general convex lower semicontinuous mirror potential. We show that, when initialized near the boundary of the domain of the mirror potential, their rescaled trajectories converge to a limiting mirror flow whose potential is the indicator function of the domain. In this limit, the primal variable minimizes the loss over a time-dependent hypothesis set: the subdifferential of the support function of the domain, evaluated at the dual variable. This characterization provides a general mechanism for incremental learning in mirror flows.
Code (0)
등록된 구현이 없습니다.
Tasks
Incremental LearningSimilar Papers 제목 키워드 기반
Learning to mirror speaking styles incrementally
Mirroring is the behavior in which one person subconsciously imitates the gesture, speech pattern, or attitude of another. In conversations, mirroring often signals the speakers enjoyment and engagement in their communic…
Variational Principles for Mirror Descent and Mirror Langevin Dynamics
Mirror descent, introduced by Nemirovski and Yudin in the 1970s, is a primal-dual convex optimization method that can be tailored to the geometry of the optimization problem at hand through the choice of a strongly conve…
Sinkhorn Algorithm as a Special Case of Stochastic Mirror Descent
We present a new perspective on the celebrated Sinkhorn algorithm by showing that is a special case of incremental/stochastic mirror descent. In order to see this, one should simply plug Kullback-Leibler divergence in bo…
Don't Vibe Code, Do Skele-Code: Interactive No-Code Notebooks for Subject Matter Experts to Build Lower-Cost Agentic Workflows
Skele-Code is a natural-language and graph-based interface for building workflows with AI agents, designed especially for less or non-technical users. It supports incremental, interactive notebook-style development, and …
Code GenerationIncremental Non-Gaussian Inference for SLAM Using Normalizing Flows
This paper presents normalizing flows for incremental smoothing and mapping (NF-iSAM), a novel algorithm for inferring the full posterior distribution in SLAM problems with nonlinear measurement models and non-Gaussian f…
Position