543 citations · 612 across the 34 of their papers we have counts for
8 papers · 1 filter
Demystifying the Myths and Legends of Nonconvex Convergence of SGD
Aritra Dutta, El Houcine Bergou, Soumia Boucherouite +3
Stochastic gradient descent (SGD) and its variants are the main workhorses for solving large-scale optimization problems with nonconvex objective functions. Although the convergenc…
EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders
Gulcin Baykal, Melih Kandemir, Gozde Unal
Codebook collapse is a common problem in training deep generative models with discrete representation spaces like Vector Quantized Variational Autoencoders (VQ-VAEs). We observe th…
Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
Hamish Flynn, David Reeb, Melih Kandemir +1
We present improved algorithms with worst-case regret guarantees for the stochastic linear bandit problem. The widely used "optimism in the face of uncertainty" principle reduces a…
Estimation of Counterfactual Interventions under Uncertainties
Juliane Weilbach, Sebastian Gerwinn, Melih Kandemir +1
Counterfactual analysis is intuitively performed by humans on a daily basis eg. "What should I have done differently to get the loan approved?". Such counterfactual questions also…
Sampling-Free Probabilistic Deep State-Space Models
Andreas Look, Melih Kandemir, Barbara Rakitsch +1
Many real-world dynamical systems can be described as State-Space Models (SSMs). In this formulation, each observation is emitted by a latent state, which follows first-order Marko…
Weighted Sequential Bayesian Inference for Non-Stationary Linear Contextual Bandits
Nicklas Werge, Yi-Shan Wu, Abdullah Akgül +1
In non-stationary linear contextual bandits, existing efficient algorithms typically rely on the Weighted Regularized Least-Squares (WRLS) estimator. Because WRLS only provides poi…
Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems
Andreas Look, Melih Kandemir, Barbara Rakitsch +1
Graph neural networks are often used to model interacting dynamical systems since they gracefully scale to systems with a varying and high number of agents. While there has been mu…
PAC-Bayesian Soft Actor-Critic Learning
Bahareh Tasdighi, Abdullah Akgül, Manuel Haussmann +2
Actor-critic algorithms address the dual goals of reinforcement learning (RL), policy evaluation and improvement via two separate function approximators. The practicality of this a…