Papers
Thu 25 Feb 2021
148 papers
- Off-Policy Imitation Learning from ObservationsOffline RL and imitation learning from data → Imitation learning methods
- Machine Unlearning via Algorithmic StabilityLLM safety and security → Machine unlearning
- Understanding Robustness in Teacher-Student Setting: A New PerspectiveKnowledge distillation → Federated, robust and private distillation
- Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-DistillationKnowledge distillation → General knowledge distillation methods
- Imitation Learning with Human Eye Gaze via Multi-Objective PredictionOffline RL and imitation learning from data → Robot manipulation imitation learning
- Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, OptimallyOffline RL and imitation learning from data → Imitation learning methods
- Application of Transfer Learning to Sign Language Recognition using an Inflated 3D Deep Convolutional Neural Network
- Web Table Classification based on Visual Features
- Highly Efficient Representation and Active Learning Framework and Its Application to Imbalanced Medical Image Classification
- Tax Evasion Risk Management Using a Hybrid Unsupervised Outlier Detection Method
- Inductive biases, pretraining and fine-tuning jointly account for brain responses to speech
- An Easy to Interpret Diagnostic for Approximate Inference: Symmetric Divergence Over Simulations
- BERT-based Acronym Disambiguation with Multiple Training Strategies
- Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward
- Detection of Alzheimer's Disease Using Graph-Regularized Convolutional Neural Network Based on Structural Similarity Learning of Brain Magnetic Resonance Images
- Case Level Counterfactual Reasoning in Process Mining
- Adaptable Hamiltonian neural networks
- Learning Discriminative Features using Multi-label Dual Space
- Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations
- Consistent Sparse Deep Learning: Theory and Computation
- Learning with invariances in random features and kernel models
- Motion Planning for a Pair of Tethered Robots
- Online Multi-Armed Bandits with Adaptive Inference
- Named Tensor Notation
- Reinforcement Learning of Implicit and Explicit Control Flow in Instructions
- Machine Biometrics -- Towards Identifying Machines in a Smart City Environment
- Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data
- Towards a Unified Framework for Fair and Stable Graph Representation Learning
- Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
- MIND: Inductive Mutual Information Estimation, A Convex Maximum-Entropy Copula Approach
- Efficient and Interpretable Robot Manipulation with Graph Neural Networks
- A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning
- Unfounded Sets for Disjunctive Hybrid MKNF Knowledge Bases
- Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling
- Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency
- Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning
- Robust Pollen Imagery Classification with Generative Modeling and Mixup Training
- PharmKE: Knowledge Extraction Platform for Pharmaceutical Texts using Transfer Learning
- Automated essay scoring using efficient transformer-based language models
- Graph Community Detection from Coarse Measurements: Recovery Conditions for the Coarsened Weighted Stochastic Block Model
- ANEA: Distant Supervision for Low-Resource Named Entity Recognition
- An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization
- DeepSZ: Identification of Sunyaev-Zel'dovich Galaxy Clusters using Deep Learning
- Federated Multi-armed Bandits with Personalization
- Task-Agnostic Morphology Evolution
- Toward Instance-Optimal State Certification With Incoherent Measurements
- Quantitative approximation results for complex-valued neural networks
- IBRNet: Learning Multi-View Image-Based Rendering
- On The Effect of Auxiliary Tasks on Representation Dynamics
- Simple multi-dataset detection
- Towards Robust Graph Contrastive Learning
- Quantization Algorithms for Random Fourier Features
- Benchmarking and Survey of Explanation Methods for Black Box Models
- Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians
- Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron
- Truncated Log-concave Sampling with Reflective Hamiltonian Monte Carlo
- On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
- Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods
- Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
- SPINN: Sparse, Physics-based, and partially Interpretable Neural Networks for PDEs
- AutoPreview: A Framework for Autopilot Behavior Understanding
- Retrieval Augmentation for Deep Neural Networks
- Batched Neural Bandits
- Multifidelity Ensemble Kalman Filtering Using Surrogate Models Defined by Physics-Informed Autoencoders
- Investigating the Limitations of Transformers with Simple Arithmetic Tasks
- Learning for Unconstrained Space-Time Video Super-Resolution
- t-SNE, Forceful Colorings and Mean Field Limits
- Towards Unbiased and Accurate Deferral to Multiple Experts
- An introduction to distributed training of deep neural networks for segmentation tasks with large seismic datasets
- Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation
- Metal-Oxide Sensor Array for Selective Gas Detection in Mixtures
- A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives
- Non-invasive Cognitive-level Human Interfacing for the Robotic Restoration of Reaching & Grasping
- Are pre-trained text representations useful for multilingual and multi-dimensional language proficiency modeling?
- A statistical framework for efficient out of distribution detection in deep neural networks
- Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning
- On regret bounds for continual single-index learning
- Stein Variational Gradient Descent: many-particle and long-time asymptotics
- Structured Prediction for CRiSP Inverse Kinematics Learning with Misspecified Robot Models
- Persistent Homology and Graphs Representation Learning
- Visualizing MuZero Models
- Machine Learning-Based Optimal Mesh Generation in Computational Fluid Dynamics
- Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning
- Distribution-Free Robust Linear Regression
- Dual MINE-based Neural Secure Communications under Gaussian Wiretap Channel
- Blocks World Revisited: The Effect of Self-Occlusion on Classification by Convolutional Neural Networks
- Self-Tuning for Data-Efficient Deep Learning
- ShuffleUNet: Super resolution of diffusion-weighted MRIs using deep learning
- TELESTO: A Graph Neural Network Model for Anomaly Classification in Cloud Services
- SparseBERT: Rethinking the Importance Analysis in Self-attention
- FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation
- Emotion-Aware, Emotion-Agnostic, or Automatic: Corpus Creation Strategies to Obtain Cognitive Event Appraisal Annotations
- CausalX: Causal Explanations and Block Multilinear Factor Analysis
- QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer
- Generalized Adversarial Distances to Efficiently Discover Classifier Errors
- Spanish Biomedical and Clinical Language Embeddings
- MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
- A deep perceptual metric for 3D point clouds
- Diffusion Earth Mover's Distance and Distribution Embeddings
- Automatic Classification of OSA related Snoring Signals from Nocturnal Audio Recordings
All 148
- ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning
- Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints
- FAITH: Fast iterative half-plane focus of expansion estimation using event-based optic flow
- Hyperparameter Transfer Learning with Adaptive Complexity
- SCD: A Stacked Carton Dataset for Detection and Segmentation
- Cognitive network science for understanding online social cognitions: A brief review
- Mixed Variable Bayesian Optimization with Frequency Modulated Kernels
- Do Input Gradients Highlight Discriminative Features?
- IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation
- A New Neuromorphic Computing Approach for Epileptic Seizure Prediction
- No-Regret Reinforcement Learning with Heavy-Tailed Rewards
- Domain Adaptation for Learning Generator from Paired Few-Shot Data
- Reducing Labelled Data Requirement for Pneumonia Segmentation using Image Augmentations
- Binary segmentation of medical images using implicit spline representations and deep learning
- CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexity
- Coarse-to-fine Airway Segmentation Using Multi information Fusion Network and CNN-based Region Growing
- Blockchained Federated Learning for Threat Defense
- Time-Series Imputation with Wasserstein Interpolation for Optimal Look-Ahead-Bias and Variance Tradeoff
- Distributed Online Learning with Multiple Kernels
- Improving Approximate Optimal Transport Distances using Quantization
- Scene Retrieval for Contextual Visual Mapping
- On Interpretability and Similarity in Concept-Based Machine Learning
- Combinatorial Bandits under Strategic Manipulations
- LazyFormer: Self Attention with Lazy Update
- Sentiment Analysis of Persian-English Code-mixed Texts
- Learning orbital dynamics of binary black hole systems from gravitational wave measurements
- A Local Method for Identifying Causal Relations under Markov Equivalence
- Confidence Calibration with Bounded Error Using Transformations
- Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data
- Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
- LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching
- Real-Time Ellipse Detection for Robotics Applications
- ISALT: Inference-based schemes adaptive to large time-stepping for locally Lipschitz ergodic systems
- Learning-based Robust Motion Planning with Guaranteed Stability: A Contraction Theory Approach
- MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition
- Online Learning for Unknown Partially Observable MDPs
- Distributionally Robust Federated Averaging
- Deep Stochastic Volatility Model
- Stochastic Aggregation in Graph Neural Networks
- Spanning Tree Constrained Determinantal Point Processes are Hard to (Approximately) Evaluate
- Provable Compressed Sensing with Generative Priors via Langevin Dynamics
- CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results
- Automatic Story Generation: Challenges and Attempts
- How to represent part-whole hierarchies in a neural network
- Modular Object-Oriented Games: A Task Framework for Reinforcement Learning, Psychology, and Neuroscience
- Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series
- Improved Regret Bound and Experience Replay in Regularized Policy Iteration
- Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret