{"total":113,"rows":[{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680,"area":null},{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101,"area":null},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70,"area":null},{"id":"2402.00809","title":"Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI","created":"2024-02-01","cited_by_count":62,"area":null},{"id":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61,"area":null},{"id":"2101.08687","title":"Overfitting for Fun and Profit: Instance-Adaptive Data Compression","created":"2021-01-21","cited_by_count":38,"area":null},{"id":"2109.13318","title":"Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation","created":"2021-09-01","cited_by_count":35,"area":null},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32,"area":null},{"id":"2210.00965","title":"Green Learning: Introduction, Examples and Outlook","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2102.13229","title":"Consistent Sparse Deep Learning: Theory and Computation","created":"2021-02-25","cited_by_count":27,"area":null},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2310.16484","title":"Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2301.09559","title":"SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]","created":"2023-01-23","cited_by_count":18,"area":null},{"id":"2105.14594","title":"Sparse Uncertainty Representation in Deep Learning with Inducing Weights","created":"2021-05-30","cited_by_count":16,"area":null},{"id":"2108.11000","title":"Layer Adaptive Node Selection in Bayesian Neural Networks: Statistical Guarantees and Implementation Details","created":"2021-08-25","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2402.10013","title":"Bridging the Empirical-Theoretical Gap in Neural Network Formal Language Learning Using Minimum Description Length","created":"2024-02-15","cited_by_count":14,"area":null},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2205.08187","title":"Deep neural networks with dependent weights: Gaussian Process mixture limit, heavy tails, sparsity and compressibility","created":"2022-05-17","cited_by_count":13,"area":null},{"id":"2205.14283","title":"Rethinking Bayesian Learning for Data Analysis: The Art of Prior and Inference in Sparsity-Aware Modeling","created":"2022-05-28","cited_by_count":12,"area":null},{"id":"2107.01952","title":"Partition and Code: learning how to compress graphs","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2109.10795","title":"Neural network relief: a pruning algorithm based on neural activity","created":"2021-09-22","cited_by_count":10,"area":null},{"id":"2406.00332","title":"A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning","created":"2024-06-01","cited_by_count":10,"area":null},{"id":"2112.15139","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2304.01762","title":"Incorporating Unlabelled Data into Bayesian Neural Networks","created":"2023-04-04","cited_by_count":9,"area":null},{"id":"2305.14765","title":"Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2405.19816","title":"Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2102.07725","title":"Neural Network Compression for Noisy Storage Devices","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2212.02770","title":"CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification","created":"2022-12-06","cited_by_count":8,"area":null},{"id":"2102.00160","title":"Deep Model Compression based on the Training History","created":"2021-01-30","cited_by_count":7,"area":null},{"id":"2102.07927","title":"Structured Dropout Variational Inference for Bayesian Neural Networks","created":"2021-02-16","cited_by_count":7,"area":null},{"id":"2111.04558","title":"Fast and Scalable Spike and Slab Variable Selection in High-Dimensional Gaussian Processes","created":"2021-11-08","cited_by_count":7,"area":null},{"id":"2202.12154","title":"Towards Effective and Robust Neural Trojan Defenses via Input Filtering","created":"2022-02-24","cited_by_count":7,"area":null},{"id":"2204.02965","title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2402.11025","title":"Training Bayesian Neural Networks with Sparse Subspace Variational Inference","created":"2024-02-16","cited_by_count":7,"area":null},{"id":"2101.04935","title":"Single-path Bit Sharing for Automatic Loss-aware Model Compression","created":"2021-01-13","cited_by_count":6,"area":null},{"id":"2104.00896","title":"Efficacy of Bayesian Neural Networks in Active Learning","created":"2021-04-02","cited_by_count":6,"area":null},{"id":"2112.02834","title":"A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2202.01290","title":"Cyclical Pruning for Sparse Neural Networks","created":"2022-02-02","cited_by_count":6,"area":null},{"id":"2210.09134","title":"Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimization","created":"2022-10-17","cited_by_count":6,"area":null},{"id":"2410.16694","title":"Governing equation discovery of a complex system from snapshots","created":"2024-10-22","cited_by_count":6,"area":null},{"id":"2509.22445","title":"Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2205.06404","title":"Fast Conditional Network Compression Using Bayesian HyperNetworks","created":"2022-05-13","cited_by_count":5,"area":null},{"id":"2206.00794","title":"Sequential Bayesian Neural Subnetwork Ensembles","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2305.00934","title":"Variational Inference for Bayesian Neural Networks under Model and Parameter Uncertainty","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2406.04549","title":"Concurrent Training and Layer Pruning of Deep Neural Networks","created":"2024-06-06","cited_by_count":5,"area":null},{"id":"2101.11353","title":"Variational Nested Dropout","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2109.05075","title":"On the Compression of Neural Networks Using $\\ell_0$-Norm Regularization and Weight Pruning","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2308.09104","title":"Spike-and-slab shrinkage priors for structurally sparse Bayesian neural networks","created":"2023-08-17","cited_by_count":4,"area":null},{"id":"2407.00761","title":"Improving the performance of Stein variational inference through extreme sparsification of physically-constrained neural network models","created":"2024-06-30","cited_by_count":4,"area":null},{"id":"2409.02134","title":"Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks","created":"2024-09-02","cited_by_count":4,"area":null},{"id":"2102.06143","title":"Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation","created":"2021-02-11","cited_by_count":3,"area":null},{"id":"2108.06446","title":"A fast asynchronous MCMC sampler for sparse Bayesian inference","created":"2021-08-14","cited_by_count":3,"area":null},{"id":"2204.06242","title":"Encoding Domain Knowledge in Multi-view Latent Variable Models: A Bayesian Approach with Structured Sparsity","created":"2022-04-13","cited_by_count":3,"area":null},{"id":"2205.04650","title":"Robust Learning of Parsimonious Deep Neural Networks","created":"2022-05-10","cited_by_count":3,"area":null},{"id":"2206.00669","title":"Bayesian Learning to Discover Mathematical Operations in Governing Equations of Dynamic Systems","created":"2022-06-01","cited_by_count":3,"area":null},{"id":"2209.05522","title":"TEDL: A Two-stage Evidential Deep Learning Method for Classification Uncertainty Quantification","created":"2022-09-12","cited_by_count":3,"area":null},{"id":"2210.12818","title":"Pushing the Efficiency Limit Using Structured Sparse Convolutions","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2301.04414","title":"How Does Traffic Environment Quantitatively Affect the Autonomous Driving Prediction?","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2407.18707","title":"Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2505.07503","title":"Identifying Causal Direction via Variational Bayesian Compression","created":"2025-05-12","cited_by_count":3,"area":null},{"id":"2202.03770","title":"Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning","created":"2022-02-08","cited_by_count":2,"area":null},{"id":"2302.10483","title":"Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approach","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2305.03395","title":"Sparsifying Bayesian neural networks with latent binary variables and normalizing flows","created":"2023-05-05","cited_by_count":2,"area":null},{"id":"2405.00202","title":"Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2405.20573","title":"Enhancing Generative Molecular Design via Uncertainty-guided Fine-tuning of Variational Autoencoders","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2406.01345","title":"BMRS: Bayesian Model Reduction for Structured Pruning","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2407.15875","title":"Shapley Pruning for Neural Network Compression","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2505.17856","title":"Stochastic Weight Sharing for Bayesian Neural Networks","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2507.03504","title":"Information-Bottleneck Driven Binary Neural Network for Change Detection","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2110.11424","title":"Analysis of memory consumption by neural networks based on hyperparameters","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2206.00853","title":"Masked Bayesian Neural Networks : Computation and Optimality","created":"2022-06-02","cited_by_count":1,"area":null},{"id":"2207.01234","title":"Incorporating functional summary information in Bayesian neural networks using a Dirichlet process likelihood approach","created":"2022-07-04","cited_by_count":1,"area":null},{"id":"2212.12921","title":"Learning k-Level Structured Sparse Neural Networks Using Group Envelope Regularization","created":"2022-12-25","cited_by_count":1,"area":null},{"id":"2304.07613","title":"STen: Productive and Efficient Sparsity in PyTorch","created":"2023-04-15","cited_by_count":1,"area":null},{"id":"2308.02451","title":"Pruning a neural network using Bayesian inference","created":"2023-08-04","cited_by_count":1,"area":null},{"id":"2309.12095","title":"Bayesian sparsification for deep neural networks with Bayesian model reduction","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2404.07532","title":"Bayesian Federated Model Compression for Communication and Computation Efficiency","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2406.03879","title":"Decay Pruning Method: Smooth Pruning With a Self-Rectifying Procedure","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2410.24214","title":"ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2411.09127","title":"Complexity-Aware Training of Deep Neural Networks for Optimal Structure Discovery","created":"2024-11-14","cited_by_count":1,"area":null},{"id":"2412.18582","title":"Exploring Embedding Priors in Prompt-Tuning for Improved Interpretability and Control","created":"2024-12-24","cited_by_count":1,"area":null},{"id":"2503.10496","title":"Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2506.22809","title":"Learning Adapter Rank via Symmetry Breaking","created":"2025-06-28","cited_by_count":1,"area":null},{"id":"2507.22004","title":"Horseshoe Forests for High-Dimensional Causal Survival Analysis","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2605.21426","title":"Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2103.10629","title":"Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2106.13585","title":"Learning Gradual Argumentation Frameworks using Genetic Algorithms","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2110.05954","title":"Mining the Weights Knowledge for Optimizing Neural Network Structures","created":"2021-10-11","cited_by_count":0,"area":null},{"id":"2112.01675","title":"Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systems","created":"2021-12-03","cited_by_count":0,"area":null},{"id":"2203.02057","title":"Interpretable Latent Variables in Deep State Space Models","created":"2022-03-03","cited_by_count":0,"area":null},{"id":"2204.01935","title":"Nonlocal optimization of binary neural networks","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2207.08258","title":"Minimum Description Length Control","created":"2022-07-17","cited_by_count":0,"area":null},{"id":"2304.06840","title":"Structured Pruning for Multi-Task Deep Neural Networks","created":"2023-04-13","cited_by_count":0,"area":null},{"id":"2304.08411","title":"Evil from Within: Machine Learning Backdoors through Hardware Trojans","created":"2023-04-17","cited_by_count":0,"area":null}],"next_cursor":"100"}