loss surface

Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation ICML 2025 On The Fairness Impacts of Hardware Selection in Machine Learning ICML 2024 Second-order forward-mode optimization of recurrent neural networks for neuroscience NeurIPS 2024 Data Augmented Flatness-aware Gradient Projection for Continual Learning ICCV 2023 GeNAS: Neural Architecture Search with Better Generalization IJCAI 2023 Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors NeurIPS 2022 Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective ICLR 2022 ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks ICML 2021 Class Normalization for (Continual)? Generalized Zero-Shot Learning ICLR 2021 Deep Learning on a Data Diet: Finding Important Examples Early in Training NeurIPS 2021 Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling ICML 2021 Non-attracting Regions of Local Minima in Deep and Wide Neural Networks JMLR 2021 HLHLp: Quantized Neural Networks Training for Reaching Flat Minima in Loss Surface AAAI 2020 Low-loss connection of weight vectors: distribution-based approaches ICML 2020 Piecewise linear activations substantially shape the loss surfaces of neural networks ICLR 2020 Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian NeurIPS 2020 The Break-Even Point on Optimization Trajectories of Deep Neural Networks ICLR 2020 Towards Understanding and Improving the Transferability of Adversarial Examples in Deep Neural Networks ACML 2020 Deep Neural Networks with Multi-Branch Architectures Are Intrinsically Less Non-Convex AISTATS 2019 Piecewise Strong Convexity of Neural Networks NeurIPS 2019 Robustness via Curvature Regularization, and Vice Versa CVPR 2019 Small nonlinearities in activation functions create bad local minima in neural networks ICLR 2019 An Alternative View: When Does SGD Escape Local Minima? ICML 2018 Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs NeurIPS 2018 The Multilinear Structure of ReLU Networks ICML 2018