TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
Comments Accepted at International Conference in Machine Learning (ICML), 2018
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Hierarchical Imitation and Reinforcement Learning
Comments Proceedings of the 35th International Conference on Machine Learning (ICML 2018)
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
Comments Published at the International Conference on Machine Learning (ICML) 2018
Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model
Comments Accepted to ICML2018 (International Conference on Machine Learning)
Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation
Comments Accepted at ICML 2018; camera-ready version
Geometry Score: A Method For Comparing Generative Adversarial Networks
Comments ICML 2018
Learning the Reward Function for a Misspecified Model
Comments To appear at ICML 2018
Provable defenses against adversarial examples via the convex outer adversarial polytope
Comments ICML final version
Capacity Releasing Diffusion for Speed and Locality
Comments Appeared in ICML 2017. Current version added reference and discussion of work on generalized Cheeger's inequalities
Approximate Message Passing for Amplitude Based Optimization
Comments accepted by ICML; short version of arXiv:1801.01170 with more simulations and other discussions
Black Box FDR
Comments To appear at ICML'18; code available at https://github.com/tansey/bb-fdr
Noise-adding Methods of Saliency Map as Series of Higher Order Partial Derivative
Comments presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden
Towards Binary-Valued Gates for Robust LSTM Training
Comments ICML 2018
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
Comments Accepted by ICML 2018
Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations
Comments To be presented at ICML 2018; 10 pages 5 figures
Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data
Comments To appear in ICML 2018
A Spectral Approach to Gradient Estimation for Implicit Distributions
Comments To appear at ICML 2018
Scalable Natural Gradient Langevin Dynamics in Practice
Comments ICML 2018 Workshop on Non-Convex Optimization
Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms
Comments Accepted by ICML 2018
Anonymous Walk Embeddings
Comments ICML 2018
Fast Decoding in Sequence Models using Discrete Latent Variables
Comments ICML 2018
Accelerating Natural Gradient with Higher-Order Invariance
Comments ICML 2018
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions
Comments Accepted at ICML 2018. Added discussion for non-pyramidal networks and ReLU activation function
RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
Comments 12 pages, 8 figures, 2018 International Conference of Machine Learning (2018 ICML)
Composite Functional Gradient Learning of Generative Adversarial Models
Comments ICML 2018
StrassenNets: Deep Learning with a Multiplication Budget
Comments ICML 2018. Code available at https://github.com/mitscha/strassennets
A Semantic Loss Function for Deep Learning with Symbolic Knowledge
Comments This version appears in the Proceedings of the 35th International Conference on Machine Learning (ICML 2018)
Message Passing Stein Variational Gradient Descent
Comments To appear in the Proceedings of the 35th International Conference on Machine Learning (ICML 2018)
Convolutional Imputation of Matrix Networks
Comments Accepted by ICML 2018
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
Comments Accepted at ICML 2018
