lazy training

Information Transfer Across Clinical Tasks via Adaptive Parameter Optimisation AISTATS 2025 The Optimization Landscape of SGD Across the Feature Learning Strength ICLR 2025 Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning NeurIPS 2024 Grokking as the transition from lazy to rich training dynamics ICLR 2024 Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning ICML 2023 Adversarial Robustness is at Odds with Lazy Training NeurIPS 2022 Evolution of Neural Tangent Kernels under Benign and Adversarial Training NeurIPS 2022 Learning sparse features can lead to overfitting in neural networks NeurIPS 2022 Neural Networks as Kernel Learners: The Silent Alignment Effect ICLR 2022 Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) NeurIPS 2022 Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed ICML 2021 Explicit loss asymptotics in the gradient descent training of neural networks NeurIPS 2021 Beyond Lazy Training for Over-parameterized Tensor Decomposition NeurIPS 2020 Finite Depth and Width Corrections to the Neural Tangent Kernel ICLR 2020 On the linearity of large non-linear models: when and why the tangent kernel is constant NeurIPS 2020 Training Linear Neural Networks: Non-Local Convergence and Complexity Results ICML 2020 Limitations of Lazy Training of Two-layers Neural Network NeurIPS 2019 On Lazy Training in Differentiable Programming NeurIPS 2019