{"total":86,"rows":[{"id":"2310.17513","title":"The Expressive Power of Low-Rank Adaptation","created":"2023-10-26","cited_by_count":102,"area":"diffusion"},{"id":"2105.14835","title":"Towards Lower Bounds on the Depth of ReLU Neural Networks","created":"2021-05-31","cited_by_count":56,"area":null},{"id":"2406.06158","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","created":"2024-06-10","cited_by_count":42,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","cited_by_count":39,"area":null},{"id":"2104.08135","title":"Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums","created":"2021-04-16","cited_by_count":37,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2302.12553","title":"Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes","created":"2023-02-24","cited_by_count":36,"area":null},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"area":null},{"id":"2202.02340","title":"Selective Network Linearization for Efficient Private Inference","created":"2022-02-04","cited_by_count":31,"area":null},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2106.13361","title":"Multifidelity Modeling for Physics-Informed Neural Networks (PINNs)","created":"2021-06-25","cited_by_count":25,"area":null},{"id":"2402.14753","title":"Prompting a Pretrained Transformer Can Be a Universal Approximator","created":"2024-02-22","cited_by_count":25,"area":null},{"id":"2512.19941","title":"Block-Recurrent Dynamics in Vision Transformers","created":"2025-12-23","cited_by_count":20,"area":null},{"id":"2102.10492","title":"Deep ReLU Networks Preserve Expected Length","created":"2021-02-21","cited_by_count":17,"area":null},{"id":"2107.00379","title":"On the Expected Complexity of Maxout Networks","created":"2021-07-01","cited_by_count":15,"area":null},{"id":"2107.13191","title":"Neural Network Approximation of Refinable Functions","created":"2021-07-28","cited_by_count":15,"area":null},{"id":"2204.01368","title":"Training Fully Connected Neural Networks is $\\exists\\mathbb{R}$-Complete","created":"2022-04-04","cited_by_count":15,"area":null},{"id":"2412.09925","title":"Simulating Hard Attention Using Soft Attention","created":"2024-12-13","cited_by_count":15,"area":null},{"id":"2306.07212","title":"Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision","created":"2023-06-12","cited_by_count":14,"area":null},{"id":"2308.05509","title":"On the Optimal Expressive Power of ReLU DNNs and Its Application in Approximation with Kolmogorov Superposition Theorem","created":"2023-08-10","cited_by_count":13,"area":null},{"id":"2102.06635","title":"ReLU Neural Networks of Polynomial Size for Exact Maximum Flow Computation","created":"2021-02-12","cited_by_count":12,"area":null},{"id":"2209.09845","title":"Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL","created":"2022-09-20","cited_by_count":12,"area":null},{"id":"2301.00008","title":"Effects of Data Geometry in Early Deep Learning","created":"2022-12-29","cited_by_count":12,"area":null},{"id":"2401.03451","title":"Optimization Over Trained Neural Networks: Taking a Relaxing Walk","created":"2024-01-07","cited_by_count":10,"area":null},{"id":"2206.00228","title":"Lower and Upper Bounds for Numbers of Linear Regions of Graph Convolutional Networks","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2312.16483","title":"Expressivity and Approximation Properties of Deep Neural Networks with ReLU$^k$ Activation","created":"2023-12-27","cited_by_count":9,"area":null},{"id":"2210.05742","title":"Curved Representation Space of Vision Transformers","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2301.07966","title":"Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions","created":"2023-01-19","cited_by_count":8,"area":null},{"id":"2312.14276","title":"Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions","created":"2023-12-21","cited_by_count":8,"area":null},{"id":"2103.05793","title":"Universal Approximation of Residual Flows in Maximum Mean Discrepancy","created":"2021-03-10","cited_by_count":7,"area":null},{"id":"2206.00241","title":"Asymptotic Properties for Bayesian Neural Network in Besov Space","created":"2022-06-01","cited_by_count":7,"area":null},{"id":"2305.08813","title":"Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks","created":"2023-05-15","cited_by_count":6,"area":null},{"id":"2408.12270","title":"Variance reduction of diffusion model's gradients with Taylor approximation-based control variate","created":"2024-08-22","cited_by_count":6,"area":"diffusion"},{"id":"2410.23152","title":"When can classical neural networks represent quantum states?","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2305.09145","title":"Deep ReLU Networks Have Surprisingly Simple Polytopes","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2602.09009","title":"ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling","created":"2026-02-09","cited_by_count":5,"area":null},{"id":"2101.04243","title":"A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks","created":"2021-01-12","cited_by_count":4,"area":null},{"id":"2202.01919","title":"Theoretical Exploration of Solutions of Feedforward ReLU Networks","created":"2022-01-24","cited_by_count":4,"area":null},{"id":"2207.09511","title":"Approximation Power of Deep Neural Networks: an explanatory mathematical survey","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2304.07247","title":"The R-mAtrIx Net","created":"2023-04-14","cited_by_count":4,"area":null},{"id":"2305.15839","title":"Embeddings between Barron spaces with higher order activation functions","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2311.18022","title":"Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training","created":"2023-11-29","cited_by_count":4,"area":null},{"id":"2201.12795","title":"Training Thinner and Deeper Neural Networks: Jumpstart Regularization","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2204.07261","title":"Convergence and Implicit Regularization Properties of Gradient Descent for Deep Residual Networks","created":"2022-04-14","cited_by_count":3,"area":null},{"id":"2205.10760","title":"CNNs Avoid Curse of Dimensionality by Learning on Patches","created":"2022-05-22","cited_by_count":3,"area":null},{"id":"2207.07612","title":"Blessing of Nonconvexity in Deep Linear Models: Depth Flattens the Optimization Landscape Around the True Solution","created":"2022-07-15","cited_by_count":3,"area":null},{"id":"2210.05212","title":"On Scrambling Phenomena for Randomly Initialized Recurrent Networks","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2306.09380","title":"Understanding Parameter Sharing in Transformers","created":"2023-06-15","cited_by_count":3,"area":null},{"id":"2502.09954","title":"On Space Folds of ReLU Neural Networks","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2110.10295","title":"Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem","created":"2021-10-19","cited_by_count":2,"area":null},{"id":"2111.12963","title":"Error Bounds for a Matrix-Vector Product Approximation with Deep ReLU Neural Networks","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2210.00805","title":"Limitations of neural network training due to numerical instability of backpropagation","created":"2022-10-03","cited_by_count":2,"area":null},{"id":"2402.02407","title":"Defining Neural Network Architecture through Polytope Structures of Dataset","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2404.17461","title":"Multi-layer random features and the approximation power of neural networks","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2504.04847","title":"Nonlocal techniques for the analysis of deep ReLU neural network approximations","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2506.19144","title":"Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2101.07126","title":"A simple geometric proof for the benefit of depth in ReLU networks","created":"2021-01-18","cited_by_count":1,"area":null},{"id":"2201.06658","title":"Learning Neural Ranking Models Online from Implicit User Feedback","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2208.07498","title":"Universal Solutions of Feedforward ReLU Networks for Interpolations","created":"2022-08-16","cited_by_count":1,"area":null},{"id":"2301.06956","title":"Expected Gradients of Maxout Networks and Consequences to Parameter Initialization","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2303.03544","title":"Expressivity of Shallow and Deep Neural Networks for Polynomial Approximation","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2307.00919","title":"Why do CNNs excel at feature extraction? A mathematical explanation","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2401.12113","title":"Extracting Formulae in Many-Valued Logic from Deep Neural Networks","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2510.10706","title":"Designing ReLU Generative Networks to Enumerate Trees with a Given Tree Edit Distance","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2606.26705","title":"Algorithmic Foundations of Deep Learning: Complexity-Theoretic Rates and a Characterization of Universal Approximation","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2103.12686","title":"PAC-learning gains of Turing machines over circuits and neural networks","created":"2021-03-23","cited_by_count":0,"area":null},{"id":"2210.12054","title":"Towards Global Neural Network Abstractions with Locally-Exact Reconstruction","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2301.13091","title":"Optimal Approximation Complexity of High-Dimensional Functions with Neural Networks","created":"2023-01-30","cited_by_count":0,"area":null},{"id":"2305.05948","title":"Multi-Path Transformer is Better: A Case Study on Neural Machine Translation","created":"2023-05-10","cited_by_count":0,"area":null},{"id":"2406.01424","title":"Universal In-Context Approximation By Prompting Fully Recurrent Models","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2407.03851","title":"Implicit Hypersurface Approximation Capacity in Deep ReLU Networks","created":"2024-07-04","cited_by_count":0,"area":null},{"id":"2411.19819","title":"GradAlign for Training-free Model Performance Inference","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2503.22082","title":"ReLU Networks as Random Functions: Their Distribution in Probability Space","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2504.18017","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2505.01985","title":"Optimization over Trained (and Sparse) Neural Networks: A Surrogate within a Surrogate","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2506.19104","title":"On the algorithmic construction of deep ReLU networks","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2601.18264","title":"Neural Network Approximation: A View from Polytope Decomposition","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.14495","title":"Divine Benevolence is an $x^2$: GLUs scale asymptotically faster than MLPs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.22660","title":"Bounding Box Anomaly Scoring for simple and efficient Out-of-Distribution detection","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.02201","title":"On the Role of Depth in the Expressivity of RNNs","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.05929","title":"ReLU Networks for Exact Generation of Similar Graphs","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.21451","title":"Approximation Theory for Neural Networks: Old and New","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.07014","title":"Local large deviations for linear-region growth in random piecewise-linear networks","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.10589","title":"Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2610.20229","title":"The minimal width of neural networks and immersions of real projective space","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}