Papers
Wed 9 Feb 2022
140 papers
- Transfer Q-learningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
- Bayesian Nonparametrics for Offline Skill DiscoveryOffline RL and imitation learning from data → Offline RL algorithms
- Offline Reinforcement Learning with Realizability and Single-policy ConcentrabilityOffline RL and imitation learning from data → Offline RL algorithms
- Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RLOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
- Imitation Learning by State-Only Distribution MatchingOffline RL and imitation learning from data → Imitation learning methods
- Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation LearningKnowledge distillation → Detection and dense prediction distillation
- AI-based approach for improving the detection of blood doping in sports
- Allocating Duplicate Copies for IoT Data in Cloud Computing Based on Harmony Search Algorithm
- High-performance automatic categorization and attribution of inventory catalogs
- Understanding and Shifting Preferences for Battery Electric Vehicles
- Mathematical Cookbook for Snapshot Compressive Imaging
- Neural Architecture Search for Energy Efficient Always-on Audio Models
- Application of the Affinity Propagation Clustering Technique to obtain traffic accident clusters at macro, meso, and micro levels
- Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity Estimation
- Dimensional criterion for forecasting nonlinear systems by reservoir computing
- SHAS: Approaching optimal Segmentation for End-to-End Speech Translation
- A Neural Network Model of Continual Learning with Cognitive Control
- Sampling Strategy for Fine-Tuning Segmentation Models to Crisis Area under Scarcity of Data
- Discovering Concepts in Learned Representations using Statistical Inference and Interactive Visualization
- "This is Fake! Shared it by Mistake": Assessing the Intent of Fake News Spreaders
- Estimation of Clinical Workload and Patient Activity using Deep Learning and Optical Flow
- Robust Bayesian Inference for Simulator-based Models via the MMD Posterior Bootstrap
- FedQAS: Privacy-aware machine reading comprehension with federated learning
- Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
- Online Learning to Transport via the Minimal Selection Principle
- Graph Neural Network for Cell Tracking in Microscopy Videos
- Predicting Human Similarity Judgments Using Large Language Models
- TamilEmo: Finegrained Emotion Detection Dataset for Tamil
- New Projection-free Algorithms for Online Convex Optimization with Adaptive Regret Guarantees
- Multivariate Analysis for Multiple Network Data via Semi-Symmetric Tensor PCA
- Designing Closed Human-in-the-loop Deferral Pipelines
- PINs: Progressive Implicit Networks for Multi-Scale Neural Representations
- Active Learning Improves Performance on Symbolic RegressionTasks in StackGP
- Deploying Vaccine Distribution Sites for Improved Accessibility and Equity to Support Pandemic Response
- Smoothed Online Learning is as Easy as Statistical Learning
- Lifting-based variational multiclass segmentation algorithm: design, convergence analysis, and implementation with applications in medical imaging
- Non-Linear Spectral Dimensionality Reduction Under Uncertainty
- Can Humans Do Less-Than-One-Shot Learning?
- Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network
- A survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problems
- Multi-modal unsupervised brain image registration using edge maps
- FCM-DNN: diagnosing coronary artery disease by deep accuracy Fuzzy C-Means clustering model
- Dimensionally Consistent Learning with Buckingham Pi
- Sharper Rates for Separable Minimax and Finite Sum Optimization via Primal-Dual Extragradient Methods
- Point-Level Region Contrast for Object Detection Pre-Training
- A Local Geometric Interpretation of Feature Extraction in Deep Feedforward Neural Networks
- Reducing Redundancy in the Bottleneck Representation of the Autoencoders
- Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration
- Automated Distance Estimation for Wildlife Camera Trapping
- Task Modifiers for HTN Planning and Acting
- Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo
- Reproducibility in Optimization: Theoretical Framework and Limits
- Exploring Structural Sparsity in Neural Image Compression
- Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models
- Stability Analysis of Recurrent Neural Networks by IQC with Copositive Mutipliers
- Adjoint-aided inference of Gaussian process driven differential equations
- Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations
- Noise fingerprints in quantum computers: Machine learning software tools
- Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
- Optimal Hyperparameters and Structure Setting of Multi-Objective Robust CNN Systems via Generalized Taguchi Method and Objective Vector Norm
- Precision Radiotherapy via Information Integration of Expert Human Knowledge and AI Recommendation to Optimize Clinical Decision Making
- Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models
- Generating Training Data with Language Models: Towards Zero-Shot Language Understanding
- NIMBLE: A Non-rigid Hand Model with Bones and Muscles
- An Exploration of Multicalibration Uniform Convergence Bounds
- Multimodal Audio-Visual Information Fusion using Canonical-Correlated Graph Neural Network for Energy-Efficient Speech Enhancement
- Explainable Predictive Modeling for Limited Spectral Data
- Obtaining Dyadic Fairness by Optimal Transport
- A Neural Network based Framework for Effective Laparoscopic Video Quality Assessment
- Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time
- The no-free-lunch theorems of supervised learning
- Optimal learning rate schedules in high-dimensional non-convex optimization problems
- Optimising hadronic collider simulations using amplitude neural networks
- Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers
- Contextualize Me -- The Case for Context in Reinforcement Learning
- Lightweight Jet Reconstruction and Identification as an Object Detection Task
- Recurrent Spectral Network (RSN): shaping the basin of attraction of a discrete map to reach automated classification
- CRAT-Pred: Vehicle Trajectory Prediction with Crystal Graph Convolutional Neural Networks and Multi-Head Self-Attention
- Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget
- False Memory Formation in Continual Learners Through Imperceptible Backdoor Trigger
- Predicting the intended action using internal simulation of perception
- Conditional Drums Generation using Compound Word Representations
- Social Media as an Instant Source of Feedback on Water Quality
- Object-Guided Day-Night Visual Localization in Urban Scenes
- Adapting to Mixing Time in Stochastic Optimization with Markovian Data
- Revisiting QMIX: Discriminative Credit Assignment by Gradient Entropy Regularization
- Deep Feature Rotation for Multimodal Image Style Transfer
- Agree to Disagree: Diversity through Disagreement for Better Transferability
- A.I. and Data-Driven Mobility at Volkswagen Financial Services AG
- A hypothesis-driven method based on machine learning for neuroimaging data analysis
- Model Architecture Adaption for Bayesian Neural Networks
- Empirical Risk Minimization with Relative Entropy Regularization: Optimality and Sensitivity Analysis
- Leveraging Experience in Lifelong Multi-Agent Pathfinding
- Improving short-term bike sharing demand forecast through an irregular convolutional neural network
- A new perspective on classification: optimally allocating limited resources to uncertain tasks
- A Reinforcement Learning Approach to Domain-Knowledge Inclusion Using Grammar Guided Symbolic Regression
- Cost-effective Framework for Gradual Domain Adaptation with Multifidelity
- House Price Valuation Model Based on Geographically Neural Network Weighted Regression: The Case Study of Shenzhen, China
- Generalized Strategic Classification and the Case of Aligned Incentives
- pNLP-Mixer: an Efficient all-MLP Architecture for Language
All 140
- MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration
- Gradient Methods Provably Converge to Non-Robust Networks
- Scenario-Assisted Deep Reinforcement Learning
- Anchor Graph Structure Fusion Hashing for Cross-Modal Similarity Search
- Identifying Backdoor Attacks in Federated Learning via Anomaly Detection
- Vertical Federated Learning: Challenges, Methodologies and Experiments
- Conditional Motion In-betweening
- Can Open Domain Question Answering Systems Answer Visual Knowledge Questions?
- TinyM2Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny Devices
- On the Implicit Bias of Gradient Descent for Temporal Extrapolation
- Log-based Anomaly Detection with Deep Learning: How Far Are We?
- Image Difference Captioning with Pre-training and Contrastive Learning
- A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization
- On Almost Sure Convergence Rates of Stochastic Gradient Methods
- Optimal Clustering with Bandit Feedback
- L2B: Learning to Bootstrap Robust Models for Combating Label Noise
- Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation
- A decision-tree framework to select optimal box-sizes for product shipments
- Adversarial Detection without Model Information
- MMLN: Leveraging Domain Knowledge for Multimodal Diagnosis
- Parsimonious Learning-Augmented Caching
- The Volcspeech system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge
- A Data-Driven Approach to Robust Hypothesis Testing Using Sinkhorn Uncertainty Sets
- GiraffeDet: A Heavy-Neck Paradigm for Object Detection
- Improving greedy core-set configurations for active learning with uncertainty-scaled distances
- Regulatory Instruments for Fair Personalized Pricing
- Motion-Aware Transformer For Occluded Person Re-identification
- A multiscale spatiotemporal approach for smallholder irrigation detection
- Parametric t-Stochastic Neighbor Embedding With Quantum Neural Network
- Learning Robust Convolutional Neural Networks with Relevant Feature Focusing via Explanations
- Data-Driven Online Interactive Bidding Strategy for Demand Response
- Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations
- Deep Neural Networks to Correct Sub-Precision Errors in CFD
- Real-Time Event-Based Tracking and Detection for Maritime Environments
- Intelligent Autonomous Intersection Management
- Improving Computational Complexity in Statistical Models with Second-Order Information
- Managers versus Machines: Do Algorithms Replicate Human Intuition in Credit Ratings?
- Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery
- Validating Causal Inference Methods
- Covariate-informed Representation Learning to Prevent Posterior Collapse of iVAE