Antonio Orvieto

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 50

Top Topics

Riemannian Manifolds

Optimization Methods

Top Venues

Publications

Antonio Orvieto, Lin Xiao
An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes. CoRR (2024)
Nicolas Zucchet, Antonio Orvieto
Recurrent neural networks: vanishing and exploding gradients are not the end of the story. CoRR (2024)
Si Yi Meng, Antonio Orvieto, Daniel Yiming Cao, Christopher De Sa
Gradient Descent on Logistic Regression with Non-Separable Data and Large Step Sizes. CoRR (2024)
Enea Monzio Compagnoni, Antonio Orvieto, Hans Kersting, Frank Norbert Proske, Aurélien Lucchi
SDEs for Minimax Optimization. CoRR (2024)
Diganta Misra, Jay Gala, Antonio Orvieto
On the low-shot transferability of [V]-Mamba. CoRR (2024)
Nicola Muca Cirone, Antonio Orvieto, Benjamin Walker, Cristopher Salvi, Terry J. Lyons
Theoretical Foundations of Deep Selective State-Space Models. CoRR (2024)
Jerome Sieber, Carmen Amo Alonso, Alexandre Didier, Melanie N. Zeilinger, Antonio Orvieto
Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks. CoRR (2024)
Lorenzo Noci, Alexandru Meterez, Thomas Hofmann, Antonio Orvieto
Why do Learning Rates Transfer? Reconciling Optimization and Scaling Limits for Deep Learning. CoRR (2024)
Enea Monzio Compagnoni, Antonio Orvieto, Hans Kersting, Frank Proske, Aurélien Lucchi
SDEs for Minimax Optimization. AISTATS (2024)
Antonio Orvieto, Anant Raj, Hans Kersting, Francis R. Bach
Explicit Regularization in Overparametrized Models via Noise Injection. AISTATS (2023)
Antonio Orvieto, Samuel L. Smith, Albert Gu, Anushan Fernando, Çaglar Gülçehre, Razvan Pascanu, Soham De
Resurrecting Recurrent Neural Networks for Long Sequences. ICML (2023)
Sanghwan Kim, Lorenzo Noci, Antonio Orvieto, Thomas Hofmann
Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning. CVPR (2023)
Enea Monzio Compagnoni, Luca Biggio, Antonio Orvieto, Frank Norbert Proske, Hans Kersting, Aurélien Lucchi
An SDE for Modeling SAM: Theory and Insights. ICML (2023)
Enea Monzio Compagnoni, Anna Scampicchio, Luca Biggio, Antonio Orvieto, Thomas Hofmann, Josef Teichmann
On the effectiveness of Randomized Signatures as Reservoir for Learning Rough Dynamics. IJCNN (2023)
Antonio Orvieto, Samuel L. Smith, Albert Gu, Anushan Fernando, Çaglar Gülçehre, Razvan Pascanu, Soham De
Resurrecting Recurrent Neural Networks for Long Sequences. CoRR (2023)
Enea Monzio Compagnoni, Antonio Orvieto, Luca Biggio, Hans Kersting, Frank Norbert Proske, Aurélien Lucchi
An SDE for Modeling SAM: Theory and Insights. CoRR (2023)
Antonio Orvieto, Soham De, Çaglar Gülçehre, Razvan Pascanu, Samuel L. Smith
On the Universality of Linear Recurrences Followed by Nonlinear Projections. CoRR (2023)
Sanghwan Kim, Lorenzo Noci, Antonio Orvieto, Thomas Hofmann
Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning. CoRR (2023)
Yuhui Ding, Antonio Orvieto, Bobby He, Thomas Hofmann
Recurrent Distance-Encoding Neural Networks for Graph Representation Learning. CoRR (2023)
Antonio Orvieto, Hans Kersting, Frank Proske, Francis R. Bach, Aurélien Lucchi
Anticorrelated Noise Injection for Improved Generalization. ICML (2022)
Aurélien Lucchi, Frank Proske, Antonio Orvieto, Francis R. Bach, Hans Kersting
On the Theoretical Properties of Noise Correlation in Stochastic Optimization. CoRR (2022)
Antonio Orvieto, Anant Raj, Hans Kersting, Francis R. Bach
Explicit Regularization in Overparametrized Models via Noise Injection. CoRR (2022)
Junchi Yang, Antonio Orvieto, Aurélien Lucchi, Niao He
Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity. AISTATS (2022)
Antonio Orvieto, Hans Kersting, Frank Proske, Francis R. Bach, Aurélien Lucchi
Anticorrelated Noise Injection for Improved Generalization. CoRR (2022)
Antonio Orvieto, Simon Lacoste-Julien, Nicolas Loizou
Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution. NeurIPS (2022)
Lorenzo Noci, Sotiris Anagnostidis, Luca Biggio, Antonio Orvieto, Sidak Pal Singh, Aurélien Lucchi
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse. CoRR (2022)
Antonio Orvieto, Jonas Kohler, Dario Pavllo, Thomas Hofmann, Aurélien Lucchi
Vanishing Curvature in Randomly Initialized Deep ReLU Networks. AISTATS (2022)
Lorenzo Noci, Sotiris Anagnostidis, Luca Biggio, Antonio Orvieto, Sidak Pal Singh, Aurélien Lucchi
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse. NeurIPS (2022)
Enea Monzio Compagnoni, Luca Biggio, Antonio Orvieto, Thomas Hofmann, Josef Teichmann
Randomized Signature Layers for Signal Extraction in Time Series Data. CoRR (2022)
Aurélien Lucchi, Frank Proske, Antonio Orvieto, Francis R. Bach, Hans Kersting
On the Theoretical Properties of Noise Correlation in Stochastic Optimization. NeurIPS (2022)
Foivos Alimisis, Antonio Orvieto, Gary Bécigneul, Aurélien Lucchi
Momentum Improves Optimization on Riemannian Manifolds. AISTATS (2021)
Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand
Rethinking the Variational Interpretation of Accelerated Optimization Methods. NeurIPS (2021)
Aurélien Lucchi, Antonio Orvieto, Adamos Solomou
On the Second-order Convergence Properties of Random Search Methods. CoRR (2021)
Antonio Orvieto, Jonas Köhler, Dario Pavllo, Thomas Hofmann, Aurélien Lucchi
Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks. CoRR (2021)
Junchi Yang, Antonio Orvieto, Aurélien Lucchi, Niao He
Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity. CoRR (2021)
Aurélien Lucchi, Antonio Orvieto, Adamos Solomou
On the Second-order Convergence Properties of Random Search Methods. NeurIPS (2021)
Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand, Thomas Hofmann, Roy S. Smith
Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization. AISTATS (2021)
Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand, Thomas Hofmann, Roy S. Smith
Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization. CoRR (2021)
Giambattista Parascandolo, Alexander Neitz, Antonio Orvieto, Luigi Gresele, Bernhard Schölkopf
Learning explanations that are hard to vary. ICLR (2021)
Foivos Alimisis, Antonio Orvieto, Gary Bécigneul, Aurélien Lucchi
A Continuous-time Perspective for Modeling Acceleration in Riemannian Optimization. AISTATS (2020)
Nikolaos Tselepidis, Jonas Köhler, Antonio Orvieto
Two-Level K-FAC Preconditioning for Deep Learning. CoRR (2020)
Giambattista Parascandolo, Alexander Neitz, Antonio Orvieto, Luigi Gresele, Bernhard Schölkopf
Learning explanations that are hard to vary. CoRR (2020)
Yuwen Chen, Antonio Orvieto, Aurélien Lucchi
An Accelerated DFO Algorithm for Finite-sum Convex Functions. CoRR (2020)
Yuwen Chen, Antonio Orvieto, Aurélien Lucchi
An Accelerated DFO Algorithm for Finite-sum Convex Functions. ICML (2020)
Antonio Orvieto, Aurélien Lucchi
Shadowing Properties of Optimization Algorithms. CoRR (2019)
Antonio Orvieto, Aurélien Lucchi
Continuous-time Models for Stochastic Optimization Algorithms. NeurIPS (2019)
Antonio Orvieto, Aurélien Lucchi
Shadowing Properties of Optimization Algorithms. NeurIPS (2019)
Antonio Orvieto, Jonas Köhler, Aurélien Lucchi
The Role of Memory in Stochastic Optimization. UAI (2019)
Antonio Orvieto, Jonas Köhler, Aurélien Lucchi
The Role of Memory in Stochastic Optimization. CoRR (2019)
Antonio Orvieto, Aurélien Lucchi
Continuous-time Models for Stochastic Optimization Algorithms. CoRR (2018)