
Deep Bayesian Quadrature Policy Optimization
We study the problem of obtaining accurate policy gradient estimates. Th...
read it

Learning compositional functions via multiplicative weight updates
Compositionality is a basic structural feature of both biological and ar...
read it

Competitive Policy Optimization
A core challenge in policy optimization in competitive Markov decision p...
read it

Competitive Mirror Descent
Constrained competitive optimization involves multiple agents trying to ...
read it

Multipole Graph Neural Operator for Parametric Partial Differential Equations
One of the main challenges in using deep learningbased methods for simu...
read it

ChanceConstrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems
Learningbased control algorithms require collection of abundant supervi...
read it

MeshfreeFlowNet: A PhysicsConstrained Deep Continuous SpaceTime SuperResolution Framework
We propose MeshfreeFlowNet, a novel deep learningbased superresolution...
read it

Spectral Learning on Matrices and Tensors
Spectral methods have been the mainstay in several domains such as machi...
read it

Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems
We study the problem of adaptive control in partially observable linear ...
read it

Regret Bound of Adaptive Control in Linear Quadratic Gaussian (LQG) Systems
We study the problem of adaptive control in partially observable linear ...
read it

Neural Operator: Graph Kernel Network for Partial Differential Equations
The classical development of neural networks has been primarily for mapp...
read it

SemiSupervised StyleGAN for Disentanglement Learning
Disentanglement learning is crucial for obtaining disentangled represent...
read it

Regret Minimization in Partially Observable Linear Quadratic Control
We study the problem of regret minimization in partially observable line...
read it

InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers
Continuous Normalizing Flows (CNFs) have emerged as promising deep gener...
read it

Angular Visual Hardness
Although convolutional neural networks (CNNs) are inspired by the mechan...
read it

Triply Robust OffPolicy Evaluation
We propose a robust regression approach to offpolicy evaluation (OPE) f...
read it

Finding Social Media Trolls: Dynamic Keyword Selection Methods for RapidlyEvolving Online Debates
Online harassment is a significant social problem. Prevention of online ...
read it

Memory Augmented Recursive Neural Networks
Recursive neural networks have shown an impressive performance for model...
read it

Implicit competitive regularization in GANs
Generative adversarial networks (GANs) are capable of producing high qua...
read it

Multi Sense Embeddings from Topic Models
Distributed word embeddings have yielded stateoftheart performance in...
read it

OutofDistribution Detection Using Neural Rendering Generative Models
Outofdistribution (OoD) detection is a natural downstream task for dee...
read it

Directivity Modes of Earthquake Populations with Unsupervised Learning
We present a novel approach for resolving modes of rupture directivity i...
read it

Learning Causal State Representations of Partially Observable Environments
Intelligent agents can cope with sensoryrich environments by learning t...
read it

Robust Regression for Safe Exploration in Control
We study the problem of safe learning and exploration in sequential cont...
read it

Competitive Gradient Descent
We introduce a new algorithm for the numerical computation of Nash equil...
read it

Regularized Learning for Domain Adaptation under Label Shifts
We propose Regularized Learning under Label shifts (RLLS), a principled ...
read it

Stochastically RankRegularized Tensor Regression Networks
Overparametrization of deep neural networks has recently been shown to ...
read it

Multidimensional Tensor Sketch
Sketching refers to a class of randomized dimensionality reduction metho...
read it

Stochastic Linear Bandits with Hidden Low Rank Structure
Highdimensional representations often have a lower dimensional underlyi...
read it

Neural Lander: Stable Drone Landing Control using Learned Dynamics
Precise trajectory control near ground is difficult for multirotor dron...
read it

Neural Rendering Model: Joint Generation and Prediction for SemiSupervised Learning
Unsupervised and semisupervised learning are important problems that ar...
read it

Open Vocabulary Learning on Source Code with a GraphStructured Cache
Machine learning models that take computer program source code as input ...
read it

Trust Region Policy Optimization of POMDPs
We propose Generalized Trust Region Policy Optimization (GTRPO), a Reinf...
read it

signSGD with Majority Vote is Communication Efficient And Byzantine Fault Tolerant
Training neural networks on large datasets can be accelerated by distrib...
read it

SampleEfficient Deep RL with Generative Adversarial Tree Search
We propose Generative Adversarial Tree Search (GATS), a sampleefficient...
read it

Probabilistic FastText for MultiSense Word Embeddings
We introduce Probabilistic FastText, a new model for word embeddings tha...
read it

Born Again Neural Networks
Knowledge distillation (KD) consists of transferring knowledge from one ...
read it

Question Type Guided Attention in Visual Question Answering
Visual Question Answering (VQA) requires integration of feature maps wit...
read it

Stochastic Activation Pruning for Robust Adversarial Defense
Neural networks are known to be vulnerable to adversarial examples. Care...
read it

Active Learning with Partial Feedback
In the largescale multiclass setting, assigning labels often consists o...
read it

signSGD: compressed optimisation for nonconvex problems
Training large neural networks requires distributing learning across mul...
read it

Efficient Exploration through Bayesian Deep QNetworks
We propose Bayesian Deep QNetwork (BDQN), a practical Thompson sampling...
read it

Combining Symbolic and Function Evaluation Expressions In Neural Programs
Neural programming involves training neural networks to learn programs f...
read it

Learning From Noisy Singlylabeled Data
Supervised learning depends on annotated examples, which are taken to be...
read it

StrassenNets: Deep learning with a multiplication budget
A large fraction of the arithmetic operations required to evaluate deep ...
read it

Deep Active Learning for Named Entity Recognition
Deep neural networks have advanced the state of the art in named entity ...
read it

Compact Tensor Pooling for Visual Question Answering
Performing high level cognitive tasks requires the integration of featur...
read it

Experimental results : Reinforcement Learning of POMDPs using Spectral Methods
We propose a new reinforcement learning algorithm for partially observab...
read it

Reinforcement Learning in RichObservation MDPs using Spectral Methods
Designing effective explorationexploitation algorithms in Markov decisi...
read it

Homotopy Analysis for Tensor PCA
Developing efficient and guaranteed nonconvex algorithms has been an imp...
read it
Anima Anandkumar
verfied profile
Bren Professor at Caltech and Principal Scientist at NVIDIA