Constantine Caramanis

22

Papers

281

Total Citations

Papers (22)

Fast Algorithms for Robust PCA via Gradient Descent

NeurIPS 2016arXiv

More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning

NeurIPS 2016arXiv

Regularized EM Algorithms: A Unified Framework and Statistical Guarantees

Optimal Linear Estimation under Unknown Nonlinear Transform

Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion

Prospective Side Information for Latent MDPs

Contextual Pandora’s Box

Recurrent Submodular Welfare and Matroid Blocking Semi-Bandits

RL for Latent MDPs: Regret Guarantees and a Lower Bound

Non-Stationary Bandits under Recharging Payoffs: Improved Planning with Sublinear Regret

Tractable Optimality in Episodic Latent MABs

Finite-Time Logarithmic Bayes Regret Upper Bounds

Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

Binary Embedding: Fundamental Limits and Fast Algorithm

Robust Estimation of Tree Structured Gaussian Graphical Models

Primal-Dual Block Generalized Frank-Wolfe

Robust compressed sensing using generative models

Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions

Applications of Common Entropy for Causal Inference

Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking

Reinforcement Learning in Reward-Mixing MDPs