{"total":161,"rows":[{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169,"area":null},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83,"area":"rag"},{"id":"2201.10355","title":"Neural Architecture Search for Spiking Neural Networks","created":"2022-01-23","cited_by_count":53,"area":null},{"id":"2107.01562","title":"Random Neural Networks in the Infinite Width Limit as Gaussian Processes","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2104.04413","title":"Provable Repair of Deep Neural Networks","created":"2021-04-09","cited_by_count":42,"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":"2411.03688","title":"Where Do We Stand with Implicit Neural Representations? A Technical and Performance Survey","created":"2024-11-06","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":"2306.06179","title":"Hidden symmetries of ReLU networks","created":"2023-06-09","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":"2110.03109","title":"Consistent Counterfactuals for Deep Models","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2201.11968","title":"Training invariances and the low-rank phenomenon: beyond linear networks","created":"2022-01-28","cited_by_count":33,"area":null},{"id":"2211.12312","title":"Interpreting Neural Networks through the Polytope Lens","created":"2022-11-22","cited_by_count":33,"area":"mechinterp"},{"id":"2403.19232","title":"AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search","created":"2024-03-28","cited_by_count":28,"area":null},{"id":"2310.05316","title":"Understanding the Feature Norm for Out-of-Distribution Detection","created":"2023-10-09","cited_by_count":27,"area":null},{"id":"2210.07236","title":"Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions","created":"2022-10-13","cited_by_count":26,"area":null},{"id":"2210.00364","title":"DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability","created":"2022-10-01","cited_by_count":23,"area":null},{"id":"2207.07696","title":"Algorithmic Determination of the Combinatorial Structure of the Linear Regions of ReLU Neural Networks","created":"2022-07-15","cited_by_count":22,"area":null},{"id":"2206.08615","title":"On the Number of Regions of Piecewise Linear Neural Networks","created":"2022-06-17","cited_by_count":21,"area":null},{"id":"2209.04036","title":"Functional dimension of feedforward ReLU neural networks","created":"2022-09-08","cited_by_count":21,"area":null},{"id":"2107.09370","title":"An Embedding of ReLU Networks and an Analysis of their Identifiability","created":"2021-07-20","cited_by_count":20,"area":null},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2102.01621","title":"Depth separation beyond radial functions","created":"2021-02-02","cited_by_count":18,"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":"2212.14268","title":"Detection of out-of-distribution samples using binary neuron activation patterns","created":"2022-12-29","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":"2111.07183","title":"Reliably-stabilizing piecewise-affine neural network controllers","created":"2021-11-13","cited_by_count":13,"area":null},{"id":"2111.08922","title":"Traversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verification","created":"2021-11-17","cited_by_count":13,"area":null},{"id":"2202.11749","title":"Are All Linear Regions Created Equal?","created":"2022-02-23","cited_by_count":13,"area":null},{"id":"2402.12572","title":"FairProof : Confidential and Certifiable Fairness for Neural Networks","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2106.03743","title":"Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2112.05745","title":"A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis","created":"2021-12-10","cited_by_count":12,"area":null},{"id":"2210.16114","title":"Towards Reliable Neural Specifications","created":"2022-10-28","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":"2209.07376","title":"Understanding Deep Neural Function Approximation in Reinforcement Learning via $\\epsilon$-Greedy Exploration","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2212.07295","title":"Maximal Initial Learning Rates in Deep ReLU Networks","created":"2022-12-14","cited_by_count":11,"area":null},{"id":"2301.12309","title":"On the Lipschitz Constant of Deep Networks and Double Descent","created":"2023-01-28","cited_by_count":11,"area":null},{"id":"2306.17418","title":"ReLU Neural Networks, Polyhedral Decompositions, and Persistent Homolog","created":"2023-06-30","cited_by_count":10,"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":"2106.08365","title":"Test Sample Accuracy Scales with Training Sample Density in Neural Networks","created":"2021-06-15","cited_by_count":9,"area":null},{"id":"2203.11355","title":"Origami in N dimensions: How feed-forward networks manufacture linear separability","created":"2022-03-21","cited_by_count":9,"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":"2405.19816","title":"Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2412.18283","title":"On the Local Complexity of Linear Regions in Deep ReLU Networks","created":"2024-12-24","cited_by_count":9,"area":null},{"id":"2204.06062","title":"Local and global topological complexity measures OF ReLU neural network functions","created":"2022-04-12","cited_by_count":8,"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":"2401.15568","title":"Intriguing Equivalence Structures of the Embedding Space of Vision Transformers","created":"2024-01-28","cited_by_count":8,"area":null},{"id":"2404.18769","title":"Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2102.13233","title":"Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations","created":"2021-02-25","cited_by_count":7,"area":null},{"id":"2103.17174","title":"Using activation histograms to bound the number of affine regions in ReLU feed-forward neural networks","created":"2021-03-31","cited_by_count":7,"area":null},{"id":"2108.11939","title":"Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2110.08271","title":"Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations","created":"2021-10-15","cited_by_count":7,"area":null},{"id":"2110.15168","title":"Labeled sample compression schemes for complexes of oriented matroids","created":"2021-10-28","cited_by_count":7,"area":null},{"id":"2210.13611","title":"Understanding the Evolution of Linear Regions in Deep Reinforcement Learning","created":"2022-10-24","cited_by_count":7,"area":null},{"id":"2505.16716","title":"The Computational Complexity of Counting Linear Regions in ReLU Neural Networks","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2210.08339","title":"Reachable Polyhedral Marching (RPM): An Exact Analysis Tool for Deep-Learned Control Systems","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2306.05325","title":"Federated Learning under Covariate Shifts with Generalization Guarantees","created":"2023-06-08","cited_by_count":6,"area":null},{"id":"2306.11827","title":"Any Deep ReLU Network is Shallow","created":"2023-06-20","cited_by_count":6,"area":null},{"id":"2501.03017","title":"Convexity in ReLU Neural Networks: beyond ICNNs?","created":"2025-01-06","cited_by_count":6,"area":null},{"id":"2107.07696","title":"Constrained Feedforward Neural Network Training via Reachability Analysis","created":"2021-07-16","cited_by_count":5,"area":null},{"id":"2206.13581","title":"Exact Spectral Norm Regularization for Neural Networks","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2209.13394","title":"Magnitude and Angle Dynamics in Training Single ReLU Neurons","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2210.05546","title":"What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2305.09145","title":"Deep ReLU Networks Have Surprisingly Simple Polytopes","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2305.15912","title":"Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2311.00858","title":"SmoothHess: ReLU Network Feature Interactions via Stein's Lemma","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2509.22849","title":"Parameterized Hardness of Zonotope Containment and Neural Network Verification","created":"2025-09-26","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":"2110.11150","title":"Lottery Tickets with Nonzero Biases","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2203.01016","title":"The Theoretical Expressiveness of Maxpooling","created":"2022-03-02","cited_by_count":4,"area":null},{"id":"2211.17180","title":"Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2305.11417","title":"Exploring the Complexity of Deep Neural Networks through Functional Equivalence","created":"2023-05-19","cited_by_count":4,"area":null},{"id":"2310.03482","title":"The Geometric Structure of Fully-Connected ReLU Layers","created":"2023-10-05","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":"2404.14265","title":"Deep Learning as Ricci Flow","created":"2024-04-22","cited_by_count":4,"area":null},{"id":"2505.18023","title":"Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2101.05490","title":"Neural networks behave as hash encoders: An empirical study","created":"2021-01-14","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":"2301.05816","title":"Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics","created":"2023-01-14","cited_by_count":3,"area":null},{"id":"2308.02729","title":"Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networks","created":"2023-08-04","cited_by_count":3,"area":null},{"id":"2310.18725","title":"The Evolution of the Interplay Between Input Distributions and Linear Regions in Networks","created":"2023-10-28","cited_by_count":3,"area":null},{"id":"2404.04662","title":"Learning Minimal Neural Specifications","created":"2024-04-06","cited_by_count":3,"area":null},{"id":"2405.09541","title":"Spectral complexity of deep neural networks","created":"2024-05-15","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":"2504.13412","title":"How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2508.03867","title":"Constraining the outputs of ReLU neural networks","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2509.21007","title":"Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.18120","title":"Generalization Below the Edge of Stability: The Role of Data Geometry","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2602.03204","title":"Sparsity is Combinatorial Depth: Quantifying MoE Expressivity via Tropical Geometry","created":"2026-02-03","cited_by_count":3,"area":"moe"},{"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":"2211.13305","title":"Dual Graphs of Polyhedral Decompositions for the Detection of Adversarial Attacks","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2311.01356","title":"Upper and lower bounds for the Lipschitz constant of random neural networks","created":"2023-11-02","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":"2402.03629","title":"Disparate Impact on Group Accuracy of Linearization for Private Inference","created":"2024-02-06","cited_by_count":2,"area":null},{"id":"2404.06104","title":"A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes","created":"2024-04-09","cited_by_count":2,"area":null},{"id":"2405.19805","title":"Complexity of Injectivity and Verification of ReLU Neural Networks","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2505.11370","title":"Understanding Nonlinear Implicit Bias via Region Counts in Input Space","created":"2025-05-16","cited_by_count":2,"area":null}],"next_cursor":"100"}