pith. sign in

Guido Mont\'ufar

Identifiers

  • name variant Guido Mont\'ufar 0.60 · backfill

Papers (47)

  1. TriSearch: Learning to Optimize Triangulations via Bistellar Flips cs.LG · 2026 · author #2
  2. The Symmetries of Three-Layer ReLU Networks cs.LG · 2026 · author #3
  3. Stress-Testing Neural Network Verifiers with Provably Robust Instances cs.LG · 2026 · author #5
  4. Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning cs.LG · 2026 · author #3
  5. Most ReLU Networks Admit Identifiable Parameters cs.LG · 2026 · author #2
  6. Algebraic Invariants of Lightning Self-Attention math.AG · 2026 · author #3
  7. Robustness Verification of Polynomial Neural Networks stat.ML · 2026 · author #3
  8. Understanding Learning Invariance in Deep Linear Networks stat.ML · 2025 · author #2
  9. Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing cs.LG · 2025 · author #5
  10. Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression stat.ML · 2024 · author #2
  11. Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension stat.ML · 2024 · author #3
  12. Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients math.OC · 2024 · author #3
  13. The Real Tropical Geometry of Neural Networks math.CO · 2024 · author #3
  14. Benign overfitting in leaky ReLU networks with moderate input dimension cs.LG · 2024 · author #4
  15. Pull-back Geometry of Persistent Homology Encodings math.AT · 2023 · author #5
  16. Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape cs.LG · 2023 · author #4
  17. Function Space and Critical Points of Linear Convolutional Networks cs.LG · 2023 · author #2
  18. Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss stat.ML · 2023 · author #4
  19. Expected Gradients of Maxout Networks and Consequences to Parameter Initialization stat.ML · 2023 · author #2
  20. Algebraic optimization of sequential decision problems math.OC · 2022 · author #3
  21. Geometry and convergence of natural policy gradient methods math.OC · 2022 · author #2
  22. FoSR: First-order spectral rewiring for addressing oversquashing in GNNs cs.LG · 2022 · author #3
  23. Enumeration of max-pooling responses with generalized permutohedra math.CO · 2022 · author #5
  24. Oversquashing in GNNs through the lens of information contraction and graph expansion cs.LG · 2022 · author #5
  25. On the effectiveness of persistent homology math.AT · 2022 · author #2
  26. Solving infinite-horizon POMDPs with memoryless stochastic policies in state-action space cs.LG · 2022 · author #2
  27. Continuity and Additivity Properties of Information Decompositions cs.IT · 2022 · author #4
  28. Training Wasserstein GANs without gradient penalties cs.LG · 2021 · author #3
  29. Learning curves for Gaussian process regression with power-law priors and targets cs.LG · 2021 · author #3
  30. The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs math.OC · 2021 · author #2
  31. Geometry of Linear Convolutional Networks cs.LG · 2021 · author #3
  32. On the Expected Complexity of Maxout Networks stat.ML · 2021 · author #2
  33. Weisfeiler and Lehman Go Cellular: CW Networks cs.LG · 2021 · author #6
  34. Information Complexity and Generalization Bounds cs.LG · 2021 · author #2
  35. Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums math.CO · 2021 · author #1
  36. Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks cs.LG · 2021 · author #5
  37. Can neural networks learn persistent homology features? cs.LG · 2020 · author #1
  38. Distributed Learning via Filtered Hyperinterpolation on Manifolds math.NA · 2020 · author #1
  39. Implicit Bias of Gradient Descent for Mean Squared Error Regression with Two-Layer Wide Neural Networks stat.ML · 2020 · author #2
  40. Optimization Theory for ReLU Neural Networks Trained with Normalization Layers cs.LG · 2020 · author #3
  41. Wasserstein Distance to Independence Models math.OC · 2020 · author #3
  42. Stochastic Feedforward Neural Networks: Universal Approximation cs.LG · 2019 · author #2
  43. How Well Do WGANs Estimate the Wasserstein Metric? cs.LG · 2019 · author #2
  44. Factorized Mutual Information Maximization cs.IT · 2019 · author #2
  45. The Variational Deficiency Bottleneck cs.IT · 2018 · author #2
  46. Computing the Unique Information cs.IT · 2017 · author #3
  47. On the Number of Linear Regions of Deep Neural Networks stat.ML · 2014 · author #1

Mentions

  • 2506.13714 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2506.06582 #5 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2410.03988 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2403.19448 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2403.06903 #4 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2405.14630 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2403.11871 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2310.07073 #5 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2211.02105 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2305.19510 #4 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2304.05752 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2209.14978 #5 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2303.03027 #4 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2204.10982 #4 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2006.07356 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2301.06956 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2210.11790 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2206.10551 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2211.09439 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2104.08135 #1 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2208.03471 #5 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2108.01538 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2205.14098 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2110.07409 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2106.12575 #6 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2107.00379 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2110.12231 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2110.14150 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2105.01747 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2103.03212 #5 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2011.14688 #1 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 1810.11677 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2003.06725 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2007.09392 #1 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2006.06878 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 1910.09763 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 1910.03875 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 1906.05460 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 1709.07487 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 1402.1869 #1 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 1402.1869 #1 · backfill · confidence 0.70 Guido Mont\'ufar
  • 2605.30220 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2605.03601 #2 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2605.18319 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2605.17153 #5 · arxiv_oai · confidence 0.70 Guido Mont\'ufar
  • 2605.17118 #3 · arxiv_oai · confidence 0.70 Guido Mont\'ufar

Frequent Coauthors