Mihai Nica

6 papers · 2020–2024 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🏆 Keyword Champion (3) 🔥 Unstoppable · Bronze

Venues

ICLR (3) NeurIPS (2) JMLR (1)

Top co-authors

Mufan Li (2) Dan Roy (2) Yani Ioannou (1) Cameron Jakub (1) Griffin Floto (1) Anna Golubeva (1) Utku Evci (1) Mike Lasby (1) Stefan Kremer (1) Boris Hanin (1)

Research topics

Machine Learning (6) Deep Learning (4) Optimization & Theory · Machine Learning (4) Application Areas (2) Architectures (2) Artificial Intelligence (1) Mathematics & Optimization (1) Core AI (1) Mathematics (1) Models (1) Optimization & Theory · Deep Learning (1) Techniques (1)

Keywords

neural network initialization (3) relu network (2) neural network theory (1) gaussian process (1) structured sparsity (1) generative model (1) variational autoencoder (1) stochastic differential equation (1) out-of-distribution detection (1) latent space (1) dynamic sparse training (1) activation function (1) residual network (1) ood detection (1) random matrix (1) network depth (1) infinite width (1) network initialization (1) network width (1) monte carlo (1)

Papers

Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization JMLR 2024 Dynamic Sparse Training with Structured Sparsity ICLR 2024 The Tilted Variational Autoencoder: Improving Out-of-Distribution Detection ICLR 2023 The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization NeurIPS 2022 The future is log-Gaussian: ResNets and their infinite-depth-and-width limit at initialization NeurIPS 2021 Finite Depth and Width Corrections to the Neural Tangent Kernel ICLR 2020