Antonio Orvieto

GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities ACL 2026 Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise ICLR 2025 (Almost) Free Modality Stitching of Foundation Models EMNLP 2025 An uncertainty principle for Linear Recurrent Neural Networks COLT 2025 Generalized Interpolating Discrete Diffusion ICML 2025 Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture ICLR 2025 When, Where and Why to Average Weights? ICML 2025 Loss Landscape Characterization of Neural Networks without Over-Parametrization NeurIPS 2024 Recurrent Distance Filtering for Graph Representation Learning ICML 2024 Recurrent neural networks: vanishing and exploding gradients are not the end of the story NeurIPS 2024 SDEs for Minimax Optimization AISTATS 2024 Super Consistency of Neural Network Landscapes and Learning Rate Transfer NeurIPS 2024 Theoretical Foundations of Deep Selective State-Space Models NeurIPS 2024 Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks NeurIPS 2024 Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues ICML 2024 Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning CVPR 2023 An SDE for Modeling SAM: Theory and Insights ICML 2023 Explicit Regularization in Overparametrized Models via Noise Injection AISTATS 2023 Resurrecting Recurrent Neural Networks for Long Sequences ICML 2023 Anticorrelated Noise Injection for Improved Generalization ICML 2022 Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution NeurIPS 2022 Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity AISTATS 2022 On the Theoretical Properties of Noise Correlation in Stochastic Optimization NeurIPS 2022 Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse NeurIPS 2022 Vanishing Curvature in Randomly Initialized Deep ReLU Networks AISTATS 2022 Learning explanations that are hard to vary ICLR 2021 Momentum Improves Optimization on Riemannian Manifolds AISTATS 2021 On the Second-order Convergence Properties of Random Search Methods NeurIPS 2021 Rethinking the Variational Interpretation of Accelerated Optimization Methods NeurIPS 2021 Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization AISTATS 2021 A Continuous-time Perspective for Modeling Acceleration in Riemannian Optimization AISTATS 2020 An Accelerated DFO Algorithm for Finite-sum Convex Functions ICML 2020 Continuous-time Models for Stochastic Optimization Algorithms NeurIPS 2019 Shadowing Properties of Optimization Algorithms NeurIPS 2019 The Role of Memory in Stochastic Optimization UAI 2019