ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Dmitry P Vetrov

Dmitry P Vetrov

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 16, 2026, 7:03 PM AMS

10

papers

765

total citations

papers (10)

Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning

Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics

On Power Laws in Deep Ensembles

NEURIPS 2020arXiv

Involutive MCMC: a Unifying Framework

On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay

NEURIPS 2021arXiv

Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes

NEURIPS 2022arXiv

Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing

Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces

NEURIPS 2021arXiv

To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning

NEURIPS 2023arXiv

Gradual Optimization Learning for Conformational Energy Minimization