2 citations · 2 across the 3 of their papers we have counts for
3 papers
cs.LG2023
Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights
Carmel Fiscko, Aayushya Agarwal, Yihan Ruan +3
We present a stochastic first-order optimization method specialized for deep neural networks (DNNs), ECCO-DNN. This method models the optimization variable trajectory as a dynamica…
math.OC2023★ 2 cited
An Equivalent Circuit Workflow for Unconstrained Optimization
Aayushya Agarwal, Carmel Fiscko, Soummya Kar +2
We introduce a new workflow for unconstrained optimization whereby objective functions are mapped onto a physical domain to more easily design algorithms that are robust to hyperpa…
eess.SY2023
Corrected: On Confident Policy Evaluation for Factored Markov Decision Processes with Node Dropouts
Carmel Fiscko, Soummya Kar, Bruno Sinopoli
In this work we investigate an importance sampling approach for evaluating policies for a structurally time-varying factored Markov decision process (MDP), i.e. the policy's value…