conftrace_
← Techniques
Deep Learning › Techniques ›

Model Architecture

4,351 papers

Papers per year

Papers

How Do Adam and Training Strategies Help BNNs Optimization ICML 2021
Group Fisher Pruning for Practical Network Compression ICML 2021
Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies. ICML 2021
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels ICML 2021
Neural Architecture Search without Training ICML 2021
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search ICML 2021
Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search ICML 2021
Principled Simplicial Neural Networks for Trajectory Prediction ICML 2021
On the Predictability of Pruning Across Scales ICML 2021
Momentum Residual Neural Networks ICML 2021
SparseBERT: Rethinking the Importance Analysis in Self-attention ICML 2021
Nondeterminism and Instability in Neural Network Optimization ICML 2021
Synthesizer: Rethinking Self-Attention for Transformer Models ICML 2021
Sparsifying Networks via Subdifferential Inclusion ICML 2021
AlphaNet: Improved Training of Supernets with Alpha-Divergence ICML 2021
Evolving Attention with Residual Convolutions ICML 2021
Leveraging Sparse Linear Layers for Debuggable Deep Networks ICML 2021
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth ICML 2021
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss ICML 2021
Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks ICML 2021
SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks ICML 2021
HAWQ-V3: Dyadic Neural Network Quantization ICML 2021
Deep Learning for Functional Data Analysis with Adaptive Basis Layers ICML 2021
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons ICML 2021
Towards Better Robust Generalization with Shift Consistency Regularization ICML 2021