Montufar, Guido

31 publications

ICLR 2025 Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing Diaaeldin Taha, James Chapman, Marzieh Eidi, Karel Devriendt, Guido Montufar
ICLR 2025 Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression Shuang Liang, Guido Montufar
NeurIPS 2025 Low Rank Gradients and Where to Find Them Rishi Sonthalia, Michael Murray, Guido Montufar
ICML 2025 On the Local Complexity of Linear Regions in Deep ReLU Networks Niket Nikul Patel, Guido Montufar
NeurIPS 2025 Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts James Chapman, Kedar Karhadkar, Guido Montufar
NeurIPS 2024 Benign Overfitting in Leaky ReLU Networks with Moderate Input Dimension Kedar Karhadkar, Erin George, Michael Murray, Guido Montúfar, Deanna Needell
NeurIPS 2024 Bounds for the Smallest Eigenvalue of the NTK for Arbitrary Spherical Data of Arbitrary Dimension Kedar Karhadkar, Michael Murray, Guido Montúfar
TMLR 2024 Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape Kedar Karhadkar, Michael Murray, Hanna Tseran, Guido Montufar
TMLR 2024 Pull-Back Geometry of Persistent Homology Encodings Shuang Liang, Renata Turkes, Jiayi Li, Nina Otter, Guido Montufar
TMLR 2024 The Real Tropical Geometry of Neural Networks for Binary Classification Marie-Charlotte Brandenburg, Georg Loho, Guido Montufar
ICLR 2023 Characterizing the Spectrum of the NTK via a Power Series Expansion Michael Murray, Hui Jin, Benjamin Bowman, Guido Montufar
ICML 2023 Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss Pierre Bréchet, Katerina Papagiannouli, Jing An, Guido Montufar
ICML 2023 Expected Gradients of Maxout Networks and Consequences to Parameter Initialization Hanna Tseran, Guido Montufar
ICLR 2023 FoSR: First-Order Spectral Rewiring for Addressing Oversquashing in GNNs Kedar Karhadkar, Pradeep Kr. Banerjee, Guido Montufar
JMLR 2023 Implicit Bias of Gradient Descent for Mean Squared Error Regression with Two-Layer Wide Neural Networks Hui Jin, Guido Montufar
ICLR 2022 Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks Benjamin Bowman, Guido Montufar
ICLR 2022 Learning Curves for Gaussian Process Regression with Power-Law Priors and Targets Hui Jin, Pradeep Kr. Banerjee, Guido Montufar
ICLR 2022 The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs Johannes Müller, Guido Montufar
ICML 2021 How Framelets Enhance Graph Neural Networks Xuebin Zheng, Bingxin Zhou, Junbin Gao, Yuguang Wang, Pietro Lió, Ming Li, Guido Montufar
ICLRW 2021 PAC-Bayes and Information Complexity Pradeep Kr. Banerjee, Guido Montufar
ICLRW 2021 Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks Cristian Bodnar, Fabrizio Frasca, Yu Guang Wang, Nina Otter, Guido Montufar, Pietro Liò, Michael M. Bronstein
NeurIPSW 2020 Can Neural Networks Learn Persistent Homology Features? Guido Montufar, Nina Otter, Yu Guang Wang
ICML 2020 Haar Graph Pooling Yu Guang Wang, Ming Li, Zheng Ma, Guido Montufar, Xiaosheng Zhuang, Yanan Fan
ICLR 2020 Kernelized Wasserstein Natural Gradient Michael Arbel, Arthur Gretton, Wuchen Li, Guido Montufar
ICML 2020 Optimization Theory for ReLU Neural Networks Trained with Normalization Layers Yonatan Dukler, Quanquan Gu, Guido Montufar
ICML 2019 Wasserstein of Wasserstein Loss for Learning Generative Models Yonatan Dukler, Wuchen Li, Alex Lin, Guido Montufar
ICLR 2015 Deep Narrow Boltzmann Machines Are Universal Approximators Guido Montúfar
JMLR 2015 Discrete Restricted Boltzmann Machines Guido Montúfar, Jason Morton
JMLR 2015 Geometry and Expressive Power of Conditional Restricted Boltzmann Machines Guido Montúfar, Nihat Ay, Keyan Ghazi-Zahedi
ICLR 2014 On the Number of Inference Regions of Deep Feed Forward Networks with Piece-Wise Linear Activations Razvan Pascanu, Guido Montúfar, Yoshua Bengio
ICLR 2013 Discrete Restricted Boltzmann Machines Guido Montúfar, Jason Morton