{"total":56,"rows":[{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268,"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":"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":"2210.07236","title":"Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions","created":"2022-10-13","cited_by_count":26,"area":null},{"id":"2403.11871","title":"The Real Tropical Geometry of Neural Networks","created":"2024-03-18","cited_by_count":24,"area":null},{"id":"2303.17045","title":"Training Neural Networks is NP-Hard in Fixed Dimension","created":"2023-03-29","cited_by_count":23,"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":"2502.06283","title":"On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth","created":"2025-02-10","cited_by_count":18,"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":"2408.04569","title":"Activation degree thresholds and expressiveness of polynomial neural networks","created":"2024-08-08","cited_by_count":14,"area":null},{"id":"2111.08117","title":"Neural networks with linear threshold activations: structure and algorithms","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2307.09212","title":"How Many Neurons Does it Take to Approximate the Maximum?","created":"2023-07-18","cited_by_count":12,"area":null},{"id":"2505.14338","title":"Better Neural Network Expressivity: Subdividing the Simplex","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2306.08805","title":"Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classification","created":"2023-06-15","cited_by_count":11,"area":null},{"id":"2402.15315","title":"On Minimal Depth in Neural Networks","created":"2024-02-23","cited_by_count":11,"area":null},{"id":"2502.09324","title":"Depth-Bounds for Neural Networks via the Braid Arrangement","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2505.06169","title":"On the Depth of Monotone ReLU Neural Networks and ICNNs","created":"2025-05-09","cited_by_count":11,"area":null},{"id":"2310.11130","title":"Topological Expressivity of ReLU Neural Networks","created":"2023-10-17","cited_by_count":10,"area":null},{"id":"2410.04907","title":"Decomposition Polyhedra of Piecewise Linear Functions","created":"2024-10-07","cited_by_count":9,"area":null},{"id":"2411.03006","title":"Neural Networks and (Virtual) Extended Formulations","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2305.16933","title":"Representing Piecewise Linear Functions by Functions with Small Arity","created":"2023-05-26","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":"2501.03017","title":"Convexity in ReLU Neural Networks: beyond ICNNs?","created":"2025-01-06","cited_by_count":6,"area":null},{"id":"2605.03601","title":"Most ReLU Networks Admit Identifiable Parameters","created":"2026-05-05","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":"2509.22849","title":"Parameterized Hardness of Zonotope Containment and Neural Network Verification","created":"2025-09-26","cited_by_count":5,"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":"2201.12795","title":"Training Thinner and Deeper Neural Networks: Jumpstart Regularization","created":"2022-01-30","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":"2601.01417","title":"A Depth Hierarchy for Computing the Maximum in ReLU Networks via Extremal Graph Theory","created":"2026-01-04","cited_by_count":3,"area":null},{"id":"2607.21651","title":"Shallower ReLU Network Representations via Exact Linear Algebra","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2306.15157","title":"Revisiting Tropical Polynomial Division: Theory, Algorithms and Application to Neural Networks","created":"2023-06-27","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":"2406.02421","title":"Representing Piecewise-Linear Functions by Functions with Minimal Arity","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2509.05894","title":"Toric geometry of ReLU neural networks","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2511.02406","title":"Arithmetic Circuits and Neural Networks for Regular Matroids","created":"2025-11-04","cited_by_count":2,"area":null},{"id":"2607.20811","title":"New Complexity-Theoretic Frontiers of Tractability for Neural Network Training","created":"2026-07-23","cited_by_count":2,"area":null},{"id":"2305.16375","title":"Data Topology-Dependent Upper Bounds of Neural Network Widths","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2403.18415","title":"The Topos of Transformer Networks","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2503.13001","title":"Linear-Size Neural Network Representation of Piecewise Affine Functions in $\\mathbb{R}^2$","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2603.03084","title":"On the Expressive Power of Transformers for Maxout Networks and Continuous Piecewise Linear Functions","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2605.04946","title":"Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.06218","title":"AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.06300","title":"Region Seeding via Pre-Activation Regularization: A Geometric View of Piecewise Affine Neural Networks","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2209.14978","title":"Enumeration of max-pooling responses with generalized permutohedra","created":"2022-09-29","cited_by_count":0,"area":null},{"id":"2403.05809","title":"Two-hidden-layer ReLU neural networks and finite elements","created":"2024-03-09","cited_by_count":0,"area":null},{"id":"2503.13512","title":"Positivity sets of hinge functions","created":"2025-03-14","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":"2507.07779","title":"Approximation Depth of Convex Polytopes","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2509.21286","title":"Maxout Polytopes","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.07202","title":"An in-depth look at approximation via deep and narrow neural networks","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.14068","title":"On the expressivity of sparse maxout networks","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2606.21687","title":"Expressivity Saturation: Reduced Affine Region Usage Under Increasing Task Complexity","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.03815","title":"A simplex-based measure of symmetry","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.23877","title":"Every Layer Counts: An Exponential $L_2$ Depth Hierarchy for ReLU Networks","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2610.04256","title":"A Hand-Checkable Proof That Two Hidden ReLU Layers Compute the Maximum of Six Numbers","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}