conftrace_

Guido Montúfar

19 papers · 2015–2025 · 4 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+7 more ↓ 🌍 Conference Polyglot (4) 🏃 Academic Marathon (10) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird
🌍 Conference Polyglot (4) 🏃 Academic Marathon (10) 🏆 Keyword Champion (2) 🗃️ Keyword Collector (61) 💎 Century Club (19) 🔥 Unstoppable (7) Prolific Year (5)

Conferences

ICLR (7) ICML (7) JMLR (3) NIPS (2)

Papers

Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression ICLR 2025 On the Local Complexity of Linear Regions in Deep ReLU Networks ICML 2025 Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing ICLR 2025 Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension NIPS 2024 Benign overfitting in leaky ReLU networks with moderate input dimension NIPS 2024 Implicit Bias of Gradient Descent for Mean Squared Error Regression with Two-Layer Wide Neural Networks JMLR 2023 Characterizing the spectrum of the NTK via a power series expansion ICLR 2023 FoSR: First-order spectral rewiring for addressing oversquashing in GNNs ICLR 2023 Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss ICML 2023 Expected Gradients of Maxout Networks and Consequences to Parameter Initialization ICML 2023 Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks ICLR 2022 Learning Curves for Gaussian Process Regression with Power-Law Priors and Targets ICLR 2022 The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs ICLR 2022 How Framelets Enhance Graph Neural Networks ICML 2021 Optimization Theory for ReLU Neural Networks Trained with Normalization Layers ICML 2020 Haar Graph Pooling ICML 2020 Wasserstein of Wasserstein Loss for Learning Generative Models ICML 2019 Discrete Restricted Boltzmann Machines JMLR 2015 Geometry and Expressive Power of Conditional Restricted Boltzmann Machines JMLR 2015