{"total":78,"rows":[{"id":"2110.02910","title":"Equivariant Subgraph Aggregation Networks","created":"2021-10-06","cited_by_count":154,"area":null},{"id":"2105.12806","title":"A Universal Law of Robustness via Isoperimetry","created":"2021-05-26","cited_by_count":151,"area":null},{"id":"2109.00650","title":"Dash: Semi-Supervised Learning with Dynamic Thresholding","created":"2021-09-01","cited_by_count":148,"area":null},{"id":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112,"area":null},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102,"area":null},{"id":"2305.18395","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","created":"2023-05-28","cited_by_count":64,"area":"lr"},{"id":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61,"area":null},{"id":"2307.14023","title":"Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?","created":"2023-07-26","cited_by_count":47,"area":null},{"id":"2110.03187","title":"On the Optimal Memorization Power of ReLU Neural Networks","created":"2021-10-07","cited_by_count":40,"area":null},{"id":"2306.02010","title":"Memorization Capacity of Multi-Head Attention in Transformers","created":"2023-06-03","cited_by_count":40,"area":null},{"id":"2205.10217","title":"Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization","created":"2022-05-20","cited_by_count":36,"area":null},{"id":"2209.06235","title":"Improving Self-Supervised Learning by Characterizing Idealized Representations","created":"2022-09-13","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":"2303.02918","title":"Graph Positional Encoding via Random Feature Propagation","created":"2023-03-06","cited_by_count":31,"area":null},{"id":"2305.18787","title":"Universality and Limitations of Prompt Tuning","created":"2023-05-30","cited_by_count":30,"area":null},{"id":"2205.13863","title":"Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power","created":"2022-05-27","cited_by_count":23,"area":null},{"id":"2201.13094","title":"Designing Universal Causal Deep Learning Models: The Geometric (Hyper)Transformer","created":"2022-01-31","cited_by_count":22,"area":null},{"id":"2409.15318","title":"On the Complexity of Neural Computation in Superposition","created":"2024-09-05","cited_by_count":21,"area":"mechinterp"},{"id":"2309.10402","title":"Minimum width for universal approximation using ReLU networks on compact domain","created":"2023-09-19","cited_by_count":18,"area":null},{"id":"2305.19510","title":"Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape","created":"2023-05-31","cited_by_count":17,"area":null},{"id":"2310.20082","title":"Efficient Subgraph GNNs by Learning Effective Selection Policies","created":"2023-10-30","cited_by_count":17,"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":"2106.07724","title":"An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2108.00207","title":"The Separation Capacity of Random Neural Networks","created":"2021-07-31","cited_by_count":14,"area":null},{"id":"2102.09671","title":"When Are Solutions Connected in Deep Networks?","created":"2021-02-18","cited_by_count":11,"area":null},{"id":"2405.13718","title":"Next-token prediction capacity: general upper bounds and a lower bound for transformers","created":"2024-05-22","cited_by_count":11,"area":null},{"id":"2602.08499","title":"Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2212.00261","title":"Task Discovery: Finding the Tasks that Neural Networks Generalize on","created":"2022-12-01","cited_by_count":9,"area":null},{"id":"2401.09902","title":"Interplay between depth and width for interpolation in neural ODEs","created":"2024-01-18","cited_by_count":9,"area":null},{"id":"2101.07150","title":"Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples","created":"2021-01-18","cited_by_count":8,"area":null},{"id":"2210.12001","title":"When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2402.08450","title":"Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2406.09291","title":"A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening","created":"2024-06-13","cited_by_count":8,"area":null},{"id":"2404.13344","title":"GRANOLA: Adaptive Normalization for Graph Neural Networks","created":"2024-04-20","cited_by_count":7,"area":null},{"id":"2205.11716","title":"Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2211.04589","title":"Finite Sample Identification of Wide Shallow Neural Networks with Biases","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2308.02001","title":"Memory capacity of two layer neural networks with smooth activations","created":"2023-08-03","cited_by_count":5,"area":null},{"id":"2401.15121","title":"Expressive Power of ReLU and Step Networks under Floating-Point Operations","created":"2024-01-26","cited_by_count":5,"area":null},{"id":"2501.03113","title":"Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality","created":"2025-01-06","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":"2312.13807","title":"Cluster-based classification with neural ODEs via control","created":"2023-12-21","cited_by_count":4,"area":null},{"id":"2402.05696","title":"Fixed width treelike neural networks capacity analysis -- generic activations","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2505.22601","title":"Machine Unlearning under Overparameterization","created":"2025-05-28","cited_by_count":4,"area":"safety"},{"id":"2303.11247","title":"Memorization Capacity of Neural Networks with Conditional Computation","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2306.17184","title":"State space models can express n-gram languages","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2312.08244","title":"Capacity of the treelike sign perceptrons neural networks with one hidden layer -- RDT based upper bounds","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2312.08257","title":"\\emph{Lifted} RDT based capacity analysis of the 1-hidden layer treelike \\emph{sign} perceptrons neural networks","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2402.08808","title":"Depth Separation in Norm-Bounded Infinite-Width Neural Networks","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2510.24601","title":"Comparison of generalised additive models and neural networks in applications: A systematic review","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2102.08093","title":"A Law of Robustness for Weight-bounded Neural Networks","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2110.07472","title":"Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2310.00327","title":"Memorization With Neural Nets: Going Beyond the Worst Case","created":"2023-09-30","cited_by_count":2,"area":null},{"id":"2310.00729","title":"Spectral Neural Networks: Approximation Theory and Optimization Landscape","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2405.13738","title":"Interpolation with deep neural networks with non-polynomial activations: necessary and sufficient numbers of neurons","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2409.06555","title":"Constructive Universal Approximation and Finite Sample Memorization by Narrow Deep ReLU Networks","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2412.01619","title":"Representation and Regression Problems in Neural Networks: Relaxation, Generalization, and Numerics","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2502.02270","title":"Exact Sequence Interpolation with Transformers","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2104.04114","title":"A Theoretical Analysis of Learning with Noisily Labeled Data","created":"2021-04-08","cited_by_count":1,"area":null},{"id":"2105.06015","title":"Why Does Multi-Epoch Training Help?","created":"2021-05-13","cited_by_count":1,"area":null},{"id":"2201.12052","title":"Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2211.13935","title":"LU decomposition and Toeplitz decomposition of a neural network","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2411.00372","title":"Generalizability of Memorization Neural Networks","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2512.17593","title":"A Unified Representation of Neural Networks Architectures","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2602.02593","title":"Effective Frontiers: A Unification of Neural Scaling Laws","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2606.17522","title":"An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2101.11685","title":"CNN with large memory layers","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2203.00762","title":"Topic Analysis for Text with Side Data","created":"2022-03-01","cited_by_count":0,"area":null},{"id":"2407.02540","title":"Analytical Solution of a Three-layer Network with a Matrix Exponential Activation Function","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2408.00359","title":"Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2510.12440","title":"Formal Models and Convergence Analysis for Context-Aware Security Verification","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.24918","title":"Topic Analysis with Side Information: A Neural-Augmented LDA Approach","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2602.01437","title":"Theoretical Analysis of Measure Consistency Regularization for Partially Observed Data","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.12482","title":"Geometric separation and constructive universal approximation with two hidden layers","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.09589","title":"Memorization capacity of deep ReLU neural networks characterized by width and depth","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2605.24244","title":"MEDAL: Manifold Embedding Distillation via Autoencoder Learning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.14398","title":"A theoretical model for task routing in mixture-of-expert transformers","created":"2026-06-12","cited_by_count":0,"area":"moe"},{"id":"2607.11541","title":"Random Label Prediction Heads for Studying Memorization in Deep Neural Networks","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2610.05874","title":"Global Communication or Graph-Specific Memory?","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}