Kirill Struminsky
Recent Publications
- Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces (2021) NeurIPS 2021
- Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution (2020) AAAI 2020
- Low-variance Gradient Estimates for the Plackett-Luce Distribution (2019)
- The Deep Weight Prior (2019) ICLR 2019
- Quantifying Learning Guarantees for Convex but Inconsistent Surrogates (2018) NeurIPS 2018
- A New Approach for Sparse Bayesian Channel Estimation in SCMA Uplink Systems (2016)
- Robust Variational Inference (2016)