
State Entropy Maximization with Random Encoders for Efficient Exploration
Recent exploration methods have proven to be a recipe for improving samp...
read it

ModelAugmented Qlearning
In recent years, Qlearning has become indispensable for modelfree rein...
read it

MASKER: Masked Keyword Regularization for Reliable Text Classification
Pretrained language models have achieved stateoftheart accuracies on...
read it

Provable Memorization via Deep Neural Networks using Sublinear Parameters
It is known that Θ(N) parameters are sufficient for neural networks to m...
read it

Trajectorywise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning
Modelbased reinforcement learning (RL) has shown great potential in var...
read it

iMix: A Strategy for Regularizing Contrastive Representation Learning
Contrastive representation learning has shown to be an effective way of ...
read it

A Deeper Look at the Layerwise Sparsity of Magnitudebased Pruning
Recent discoveries on neural network pruning reveal that, with a careful...
read it

Fewshot Visual Reasoning with Metaanalogical Contrastive Learning
While humans can solve a visual puzzle that requires logical reasoning b...
read it

TimeReversal Symmetric ODE Network
Timereversal symmetry, which requires that the dynamics of a system sho...
read it

Distribution Aligning Refinery of Pseudolabel for Imbalanced Semisupervised Learning
While semisupervised learning (SSL) has proven to be a promising way fo...
read it

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
Novelty detection, i.e., identifying whether a given sample is drawn fro...
read it

Learning to Sample with Local and Global Contexts in Experience Replay Buffer
Experience replay, which enables the agents to remember and reuse experi...
read it

Learning from Failure: Training Debiased Classifier from Biased Classifier
Neural networks often learn to make predictions that overly rely on spur...
read it

Guiding Deep Molecular Optimization with Genetic Exploration
De novo molecular design attempts to search over the chemical space for ...
read it

Learning to Generate Noise for Robustness against Multiple Perturbations
Adversarial learning has emerged as one of the successful techniques to ...
read it

QOPT: Optimistic Value Function Decentralization for Cooperative MultiAgent Reinforcement Learning
We propose a novel valuebased algorithm for cooperative multiagent rei...
read it

Learning What to Defer for Maximum Independent Sets
Designing efficient algorithms for combinatorial optimization appears ub...
read it

Minimum Width for Universal Approximation
The universal approximation property of widthbounded networks has been ...
read it

Learning Bounds for Risksensitive Learning
In risksensitive learning, one aims to find a hypothesis that minimizes...
read it

Consistency Regularization for Certified Robustness of Smoothed Classifiers
A recent technique of randomized smoothing has shown that the worstcase...
read it

Contextaware Dynamics Model for Generalization in ModelBased Reinforcement Learning
Modelbased reinforcement learning (RL) enjoys several benefits, such as...
read it

M2m: Imbalanced Classification via Majortominor Translation
In most realworld scenarios, labeled training datasets are highly class...
read it

Regularizing Classwise Predictions via Selfknowledge Distillation
Deep neural networks with millions of parameters may suffer from poor ge...
read it

Freeze the Discriminator: a Simple Baseline for FineTuning GANs
Generative adversarial networks (GANs) have shown outstanding performanc...
read it

Freeze Discriminator: A Simple Baseline for Finetuning GANs
Generative adversarial networks (GANs) have shown outstanding performanc...
read it

Lookahead: A FarSighted Alternative of Magnitudebased Pruning
Magnitudebased pruning is one of the simplest methods for pruning neura...
read it

Mining GOLD Samples for Conditional GANs
Conditional generative adversarial networks (cGANs) have gained a consid...
read it

Rethinking Data Augmentation: SelfSupervision and SelfDistillation
Data augmentation techniques, e.g., flipping or cropping, which systemat...
read it

A Simple Randomization Technique for Generalization in Deep Reinforcement Learning
Deep reinforcement learning (RL) agents often fail to generalize to unse...
read it

Polynomial Tensor Sketch for Elementwise Function of LowRank Matrix
This paper studies how to sketch elementwise functions of lowrank matr...
read it

Learning What and Where to Transfer
As the application of deep learning has expanded to realworld problems ...
read it

Spectral Approximate Inference
Given a graphical model (GM), computing its partition function is the mo...
read it

Training CNNs with Selective Allocation of Channels
Recent progress in deep convolutional neural networks (CNNs) have enable...
read it

Incremental Learning with Unlabeled Data in the Wild
Deep neural networks are known to suffer from catastrophic forgetting in...
read it

Bitcoin vs. Bitcoin Cash: Coexistence or Downfall of Bitcoin Cash?
In Aug. 2017, Bitcoin was split into the original Bitcoin (BTC) and Bitc...
read it

Robust Inference via Generative Classifiers for Handling Noisy Labels
Largescale datasets may contain significant proportions of noisy (incor...
read it

InstaGAN: Instanceaware ImagetoImage Translation
Unsupervised imagetoimage translation has gained considerable attentio...
read it

Simulationbased Distributed Coordination Maximization over Networks
In various online/offline multiagent networked environments, it is very...
read it

A Simple Unified Framework for Detecting OutofDistribution Samples and Adversarial Attacks
Detecting test samples drawn sufficiently far away from the training dis...
read it

Anytime Neural Prediction via Slicing Networks Vertically
The pioneer deep neural networks (DNNs) have emerged to be deeper or wid...
read it

Hierarchical Novelty Detection for Visual Object Recognition
Deep neural networks have achieved impressive success in largescale vis...
read it

Bucket Renormalization for Approximate Inference
Probabilistic graphical models are a key tool in machine learning applic...
read it

Optimizing Spectral Sums using Randomized Chebyshev Expansions
The trace of matrix functions, often called spectral sums, e.g., rank, l...
read it

Gauged MiniBucket Elimination for Approximate Inference
Computing the partition function Z of a discrete graphical model is a fu...
read it

Training Confidencecalibrated Classifiers for Detecting OutofDistribution Samples
The problem of detecting whether a test sample is from indistribution (...
read it

Confident Multiple Choice Learning
Ensemble methods are arguably the most trustworthy techniques for boosti...
read it

Rapid Mixing SwendsenWang Sampler for Stochastic Partitioned Attractive Models
The Gibbs sampler is a particularly popular Markov chain used for learni...
read it

Sequential Local Learning for Latent Graphical Models
Learning parameters of latent graphical models (GM) is inherently much h...
read it

Contextual Multiarmed Bandits under Feature Uncertainty
We study contextual multiarmed bandit problems under linear realizabili...
read it

Gauging Variational Inference
Computing partition function is the most important statistical inference...
read it
Jinwoo Shin
is this you? claim profile
Assistant Professor at School of Electrical Engineering at KAIST, Korea, Ph.D. degree from Massachusetts Institute of Technology in 2010, Researcher at Algorithms & Randomness Center, Georgia Institute of Technology from 20102012, Business Analytics and Mathematical Sciences Department, IBM T. J. Watson Research from 20122013, Kenneth C. Sevcik Award at ACM SIGMETRICS/Performance 2009, Best Publication Award from INFORMS Applied Probability Society 2013, Best Paper Award at ACM MOBIHOC 2013, Bloomberg Scientific Research Award 2015 and ACM SIGMETRICS Rising Star Award 2015.