Aurelien Lucchi

Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise ICLR 2025 Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs AISTATS 2025 Cubic regularized subspace Newton for non-convex optimization AISTATS 2025 Loss Landscape Characterization of Neural Networks without Over-Parametrization NIPS 2024 Initial Guessing Bias: How Untrained Networks Favor Some Classes ICML 2024 A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression NIPS 2024 Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks NIPS 2024 Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum ICML 2024 SDEs for Minimax Optimization AISTATS 2024 Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers NIPS 2023 An SDE for Modeling SAM: Theory and Insights ICML 2023 A Theoretical Analysis of the Learning Dynamics under Class Imbalance ICML 2023 Mastering Spatial Graph Prediction of Road Networks ICCV 2023 A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression NIPS 2023 On the Theoretical Properties of Noise Correlation in Stochastic Optimization NIPS 2022 Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse NIPS 2022 Vanishing Curvature in Randomly Initialized Deep ReLU Networks AISTATS 2022 Phenomenology of Double Descent in Finite-Width Neural Networks ICLR 2022 Generalization Through the Lens of Leave-One-Out Error ICLR 2022 A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning AISTATS 2022 Anticorrelated Noise Injection for Improved Generalization ICML 2022 Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity AISTATS 2022 Neural Symbolic Regression that scales ICML 2021 Scalable Graph Networks for Particle Simulations AAAI 2021 On the Second-order Convergence Properties of Random Search Methods NIPS 2021 Learning Generative Models of Textured 3D Meshes From Real-World Images ICCV 2021 Momentum Improves Optimization on Riemannian Manifolds AISTATS 2021 Direct-Search for a Class of Stochastic Min-Max Problems AISTATS 2021 Convolutional Generation of Textured 3D Meshes NIPS 2020 Batch normalization provably avoids ranks collapse for randomly initialised deep networks NIPS 2020 A Continuous-time Perspective for Modeling Acceleration in Riemannian Optimization AISTATS 2020 Controlling Style and Semantics in Weakly-Supervised Image Generation ECCV 2020 An Accelerated DFO Algorithm for Finite-sum Convex Functions ICML 2020 Randomized Block-Diagonal Preconditioning for Parallel Learning ICML 2020 Topological Map Extraction From Overhead Images ICCV 2019 Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization AISTATS 2019 The Role of Memory in Stochastic Optimization UAI 2019 Local Saddle Point Optimization: A Curvature Exploitation Approach AISTATS 2019 A Domain Agnostic Measure for Monitoring and Evaluating GANs NIPS 2019 Shadowing Properties of Optimization Algorithms NIPS 2019 Continuous-time Models for Stochastic Optimization Algorithms NIPS 2019 Semantic Interpolation in Implicit Models ICLR 2018 Escaping Saddles with Stochastic Gradients ICML 2018 A Distributed Second-Order Algorithm You Can Trust ICML 2018 An Online Learning Approach to Generative Adversarial Networks ICLR 2018 Sub-sampled Cubic Regularization for Non-convex Optimization ICML 2017 Stabilizing Training of Generative Adversarial Networks through Regularization NIPS 2017 SwissCheese at SemEval-2016 Task 4: Sentiment Classification Using an Ensemble of Convolutional Neural Networks with Distant Supervision SEMEVAL 2016 Starting Small - Learning with Adaptive Sample Sizes ICML 2016 Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy NIPS 2016 Variance Reduced Stochastic Gradient Descent with Neighbors NIPS 2015 Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets CVPR 2013 An Optimal Policy for Target Localization with Application to Electron Microscopy ICML 2013