NeurIPS 2020 Subject Areas

Authors must choose subject areas (one primary, multiple secondary) when they submit a paper. These subject areas help the program chairs to find the most appropriate reviewers for each submission.

 

Algorithms      
∟ Active Learning      
∟ Adaptive Data Analysis      
∟ Adversarial Learning
∟ AutoML      
∟ Bandit Algorithms      
∟ Boosting and Ensemble Methods      
∟ Classification      
∟ Clustering      
∟ Collaborative Filtering      
∟ Components Analysis (e.g., CCA, ICA, LDA, PCA)    
∟Communication- or Memory-Bounded Learning
∟ Continual Learning  
∟ Data Compression
∟ Density Estimation      
∟ Dynamical Systems
∟ Few-Shot Learning    
∟ Kernel Methods      
∟ Large Margin Methods
∟ Large Scale Learning
∟ Meta-Learning      
∟ Metric Learning      
∟ Missing Data      
∟ Model Selection and Structure Learning     
∟ Multimodal Learning 
∟ Multitask and Transfer Learning      
∟ Nonlinear Dimensionality Reduction and Manifold Learning      
∟ Online Learning      
∟ Program Induction
∟ Ranking and Preference Learning      
∟ Regression      
∟ Relational Learning      
∟ Representation Learning      
∟ Semi-Supervised Learning      
∟ Similarity and Distance Learning      
∟ Sparse Coding and Dimensionality Expansion      
∟ Sparsity and Compressed Sensing      
∟ Spectral Methods      
∟ Stochastic Methods      
∟ Structured Prediction      
∟ Uncertainty Estimation
∟ Unsupervised Learning      
Applications      
∟ Activity and Event Recognition
∟ Audio and Speech Processing      
∟ Body Pose, Face, and Gesture Analysis            
∟ Computational Biology and Bioinformatics      
∟ Computational Photography      
∟ Computational Social Science      
∟ Computer Vision      
∟ Denoising      
∟ Dialog- or Communication-Based Learning      
∟ Automated Reasoning and Formal Methods
∟ Game Playing      
∟ Hardware and Systems      
∟ Health
∟ Image Segmentation      
∟ Information Retrieval      
∟ Matrix and Tensor Factorization      
∟ Motor Control      
∟ Music Modeling and Analysis      
∟ Natural Language Processing      
∟ Network Analysis      
∟ Object Detection      
∟ Object Recognition            
∟ Program Understanding and Generation      
∟ Quantitative Finance and Econometrics
∟ Quantum Learning      
∟ Recommender Systems      
∟ Robotics      
∟ Signal Processing      
∟ Speech Recognition      
∟ Sustainability      
∟ Time Series Analysis      
∟ Tracking and Motion in Video      
∟ Video Analysis      
∟ Visual Question Answering      
∟ Visual Scene Analysis and Interpretation      
∟ Web Applications and Internet Data      
Data, Challenges, Implementations, and Software      
∟ Benchmarks      
∟ Data Sets or Data Repositories      
∟ Software Toolkits      
∟ Virtual Environments      
Deep Learning      
∟ Adversarial Networks      
∟ Attention Models      
∟ Biologically Plausible Deep Networks      
∟ CNN Architectures      
∟ Deep Autoencoders      
∟ Efficient Inference Methods      
∟ Efficient Training Methods      
∟ Embedding Approaches            
∟ Generative Models      
∟ Interaction-Based Deep Networks      
∟ Memory-Augmented Neural Networks      
∟ Optimization for Deep Networks      
∟ Predictive Models            
∟ Recurrent Networks      
∟ Supervised Deep Networks      
∟ Visualization or Exposition Techniques for Deep Networks      
Neuroscience and Cognitive Science      
∟ Auditory Perception      
∟ Brain Imaging      
∟ Brain Mapping      
∟ Brain Segmentation      
∟ Brain--Computer Interfaces and Neural Prostheses      
∟ Cognitive Science      
∟ Connectomics      
∟ Human or Animal Learning      
∟ Language for Cognitive Science      
∟ Memory      
∟ Neural Coding      
∟ Neuropsychology      
∟ Neuroscience      
∟ Perception      
∟ Plasticity and Adaptation      
∟ Problem Solving      
∟ Reasoning      
∟ Spike Train Generation      
∟ Synaptic Modulation      
∟ Visual Perception      
Optimization      
∟ Discrete Optimization
∟ Convex Optimization
∟ Evolutionary Computation      
∟ Non-Convex Optimization      
∟ Submodular Optimization
∟ Stochastic Optimization      
Probabilistic Methods      
∟ Bayesian Nonparametrics      
∟ Bayesian Theory      
∟ Belief Propagation      
∟ Causal Inference      
∟ Distributed Inference      
∟ Gaussian Processes      
∟ Graphical Models      
∟ Hierarchical Models      
∟ Latent Variable Models      
∟ MCMC
∟ Probabilistic Programming      
∟ Topic Models      
∟ Variational Inference      
Reinforcement Learning and Planning      
∟ Decision and Control      
∟ Exploration      
∟ Hierarchical RL      
∟ Markov Decision Processes      
∟ Model-Based RL      
∟ Multi-Agent RL      
∟ Navigation      
∟ Planning      
∟ Reinforcement Learning      
Theory
∟ Models of Learning and Generalization      
∟ Computational Learning Theory      
∟ Control Theory      
∟ Data-driven Algorithm Design
∟ Frequentist Statistics      
∟ Game Theory and Computational Economics      
∟ Hardness of Learning and Approximations    
∟ High-Dimensional Inference  
∟ Information Theory      
∟ Large Deviations and Asymptotic Analysis      
∟ Statistical Learning Theory      
∟ Regularization      
∟ Spaces of Functions and Kernels      
∟ Statistical Physics of Learning
Social Aspects of Machine Learning
  ∟AI Safety
  ∟Fairness, Accountability, and Transparency
  ∟Privacy, Anonymity, and Security