loss landscape

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time ICML 2022 PoF: Post-Training of Feature Extractor for Improving Generalization ICML 2022 Self-ensemble Adversarial Training for Improved Robustness ICLR 2022 Sharpness-Aware Training for Free NeurIPS 2022 Symmetry Teleportation for Accelerated Optimization NeurIPS 2022 Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes NeurIPS 2022 Understanding Gradient Descent on the Edge of Stability in Deep Learning ICML 2022 Understanding Robust Overfitting of Adversarial Training and Beyond ICML 2022 What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us? ICML 2022 When Do Flat Minima Optimizers Work? NeurIPS 2022 A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization AAAI 2021 Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II NeurIPS 2021 Characterizing possible failure modes in physics-informed neural networks NeurIPS 2021 Characterizing the Loss Landscape in Non-Negative Matrix Factorization AAAI 2021 Deep Neural Networks Are Congestion Games: From Loss Landscape to Wardrop Equilibrium and Beyond AISTATS 2021 Embedding Principle of Loss Landscape of Deep Neural Networks NeurIPS 2021 Exploring the loss landscape in neural architecture search UAI 2021 Exponentially Many Local Minima in Quantum Neural Networks ICML 2021 Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances ICML 2021 Identifying untrustworthy predictions in neural networks by geometric gradient analysis UAI 2021 Learn2Hop: Learned Optimization on Rough Landscapes ICML 2021 Learning explanations that are hard to vary ICLR 2021 Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling ICML 2021 On Monotonic Linear Interpolation of Neural Network Parameters ICML 2021 On the Variance of the Fisher Information for Deep Learning NeurIPS 2021