Neural Network Optimization

Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies ICML 2021 Understanding and Improving Early Stopping for Learning with Noisy Labels NeurIPS 2021 Understanding Decoupled and Early Weight Decay AAAI 2021 Understanding Gradient Clipping In Incremental Gradient Methods AISTATS 2021 Understanding How Encoder-Decoder Architectures Attend NeurIPS 2021 Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron ACML 2021 Understanding the Dynamics of Gradient Flow in Overparameterized Linear models ICML 2021 Understanding the effects of data parallelism and sparsity on neural network training ICLR 2021 Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards a Fourier Perspective AAAI 2021 Universal approximation power of deep residual neural networks via nonlinear control theory ICLR 2021 Using Transposed Convolution for Articulatory-to-Acoustic Conversion from Real-Time MRI Data Interspeech 2021 ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search CVPR 2021 VSQL: Variational Shadow Quantum Learning for Classification AAAI 2021 Weight-covariance alignment for adversarially robust neural networks ICML 2021 What can linearized neural networks actually say about generalization? NeurIPS 2021 What training reveals about neural network complexity NeurIPS 2021 When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute EMNLP 2021 When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? JMLR 2021 When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT 2021 When does preconditioning help or hurt generalization? ICLR 2021 When Expressivity Meets Trainability: Fewer than n Neurons Can Work NeurIPS 2021 Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition ICCV 2021 3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels AAAI 2020 Accelerating Primal Solution Findings for Mixed Integer Programs Based on Solution Prediction AAAI 2020 Accelerating SGD with momentum for over-parameterized learning ICLR 2020