{"total":99,"rows":[{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377,"area":null},{"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":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86,"area":null},{"id":"2209.02128","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","created":"2022-09-05","cited_by_count":69,"area":null},{"id":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54,"area":null},{"id":"2402.02347","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","created":"2024-02-04","cited_by_count":52,"area":null},{"id":"2306.17759","title":"The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit","created":"2023-06-30","cited_by_count":47,"area":null},{"id":"2302.10322","title":"Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2206.02768","title":"The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization","created":"2022-06-06","cited_by_count":41,"area":null},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2203.08120","title":"Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers","created":"2022-03-15","cited_by_count":28,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2210.00688","title":"On the infinite-depth limit of finite-width neural networks","created":"2022-10-03","cited_by_count":22,"area":null},{"id":"2302.00453","title":"Width and Depth Limits Commute in Residual Networks","created":"2023-02-01","cited_by_count":21,"area":null},{"id":"2307.06092","title":"Quantitative CLTs in Deep Neural Networks","created":"2023-07-12","cited_by_count":20,"area":null},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2206.01342","title":"Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2110.11749","title":"Feature Learning and Signal Propagation in Deep Neural Networks","created":"2021-10-22","cited_by_count":18,"area":null},{"id":"2509.10167","title":"The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram","created":"2025-09-12","cited_by_count":17,"area":null},{"id":"2102.01732","title":"Truly Sparse Neural Networks at Scale","created":"2021-02-02","cited_by_count":16,"area":null},{"id":"2505.23194","title":"Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics","created":"2025-05-29","cited_by_count":16,"area":null},{"id":"2103.03113","title":"Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective","created":"2021-03-03","cited_by_count":14,"area":null},{"id":"2310.10767","title":"Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2506.20629","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","created":"2025-06-25","cited_by_count":14,"area":null},{"id":"2105.07741","title":"Activation function design for deep networks: linearity and effective initialisation","created":"2021-05-17","cited_by_count":13,"area":null},{"id":"2105.03332","title":"Finite volume method network for acceleration of unsteady computational fluid dynamics: non-reacting and reacting flows","created":"2021-05-07","cited_by_count":12,"area":null},{"id":"2204.14126","title":"Wide and Deep Neural Networks Achieve Optimality for Classification","created":"2022-04-29","cited_by_count":12,"area":null},{"id":"2311.18718","title":"The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2106.09798","title":"Wide stochastic networks: Gaussian limit and PAC-Bayesian training","created":"2021-06-17","cited_by_count":10,"area":null},{"id":"2405.19279","title":"Understanding and Minimising Outlier Features in Neural Network Training","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2105.08095","title":"Automatic Fault Detection for Deep Learning Programs Using Graph Transformations","created":"2021-05-17","cited_by_count":9,"area":null},{"id":"2108.06530","title":"Neuron Campaign for Initialization Guided by Information Bottleneck Theory","created":"2021-08-14","cited_by_count":9,"area":null},{"id":"2205.12379","title":"Gaussian Pre-Activations in Neural Networks: Myth or Reality?","created":"2022-05-24","cited_by_count":9,"area":null},{"id":"2410.02247","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2505.12455","title":"AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2602.06204","title":"Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2108.02316","title":"Deep Stable neural networks: large-width asymptotics and convergence rates","created":"2021-08-02","cited_by_count":8,"area":null},{"id":"2210.09809","title":"Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel","created":"2022-10-18","cited_by_count":8,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","cited_by_count":8,"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":"2106.03091","title":"Regularization in ResNet with Stochastic Depth","created":"2021-06-06","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":"2401.13558","title":"Task structure and nonlinearity jointly determine learned representational geometry","created":"2024-01-24","cited_by_count":6,"area":null},{"id":"2506.15025","title":"Optimal Embedding Learning Rate in LLMs: The Effect of Vocabulary Size","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2110.02885","title":"Bayesian neural network unit priors and generalized Weibull-tail property","created":"2021-10-06","cited_by_count":5,"area":null},{"id":"2204.12589","title":"Self-scalable Tanh (Stan): Faster Convergence and Better Generalization in Physics-informed Neural Networks","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2301.13710","title":"On the Initialisation of Wide Low-Rank Feedforward Neural Networks","created":"2023-01-31","cited_by_count":5,"area":null},{"id":"2409.10463","title":"Kolmogorov-Arnold Networks in Low-Data Regimes: A Comparative Study with Multilayer Perceptrons","created":"2024-09-16","cited_by_count":5,"area":null},{"id":"2105.00507","title":"Universal scaling laws in the gradient descent training of neural networks","created":"2021-05-02","cited_by_count":4,"area":null},{"id":"2105.10277","title":"Maximum and Leaky Maximum Propagation","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2205.05662","title":"Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis","created":"2022-05-11","cited_by_count":4,"area":null},{"id":"2210.11672","title":"Stochastic Adaptive Activation Function","created":"2022-10-21","cited_by_count":4,"area":null},{"id":"2307.02284","title":"Universal Scaling Laws of Absorbing Phase Transitions in Artificial Deep Neural Networks","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2503.08231","title":"How good is PAC-Bayes at explaining generalisation?","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2603.15389","title":"When Does Sparsity Mitigate the Curse of Depth in LLMs","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2101.04097","title":"Correlated Weights in Infinite Limits of Deep Convolutional Neural Networks","created":"2021-01-11","cited_by_count":3,"area":null},{"id":"2302.09712","title":"Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization","created":"2023-02-20","cited_by_count":3,"area":null},{"id":"2304.04784","title":"Criticality versus uniformity in deep neural networks","created":"2023-04-10","cited_by_count":3,"area":null},{"id":"2402.05401","title":"Adaptive Activation Functions for Predictive Modeling with Sparse Experimental Data","created":"2024-02-08","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":"2506.08764","title":"On the Stability of the Jacobian Matrix in Deep Neural Networks","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2511.01734","title":"A Proof of Learning Rate Transfer under $\\mu$P","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2105.08911","title":"Multi-layer Perceptron Trainability Explained via Variability","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2106.13315","title":"Generalized Unsupervised Clustering of Hyperspectral Images of Geological Targets in the Near Infrared","created":"2021-06-24","cited_by_count":2,"area":null},{"id":"2202.01210","title":"Deep Layer-wise Networks Have Closed-Form Weights","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2404.03992","title":"Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks","created":"2024-04-05","cited_by_count":2,"area":null},{"id":"2410.15578","title":"Generalized Probabilistic Attention Mechanism in Transformers","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2505.11881","title":"Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2507.05566","title":"SingLoRA: Low Rank Adaptation Using a Single Matrix","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2102.04896","title":"Formalising the Use of the Activation Function in Neural Inference","created":"2021-02-02","cited_by_count":1,"area":null},{"id":"2103.12499","title":"Initializing ReLU networks in an expressive subspace of weights","created":"2021-03-23","cited_by_count":1,"area":null},{"id":"2305.10964","title":"Learning Activation Functions for Sparse Neural Networks","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2310.01683","title":"Commutative Width and Depth Scaling in Deep Neural Networks","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2310.11439","title":"From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2410.20107","title":"Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations","created":"2024-10-26","cited_by_count":1,"area":null},{"id":"2512.06427","title":"A new initialisation to Control Gradients in Sinusoidal Neural network","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2102.00853","title":"Painless step size adaptation for SGD","created":"2021-02-01","cited_by_count":0,"area":null},{"id":"2201.10393","title":"Interspecies Collaboration in the Design of Visual Identity: A Case Study","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2205.08043","title":"Explainable and Optimally Configured Artificial Neural Networks for Attack Detection in Smart Homes","created":"2022-05-17","cited_by_count":0,"area":null},{"id":"2211.05730","title":"NEON: Enabling Efficient Support for Nonlinear Operations in Resistive RAM-based Neural Network Accelerators","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2304.10860","title":"On the Importance of Exploration for Real Life Learned Algorithms","created":"2023-04-21","cited_by_count":0,"area":null},{"id":"2306.01513","title":"Network Degeneracy as an Indicator of Training Performance: Comparing Finite and Infinite Width Angle Predictions","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2502.13110","title":"Feature Learning Beyond the Edge of Stability","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2503.02267","title":"REAct: Rational Exponential Activation for Better Learning and Generalization in PINNs","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2505.17254","title":"Approach to Finding a Robust Deep Learning Model","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2506.03184","title":"Impact of Tuning Parameters in Deep Convolutional Neural Network Using a Crack Image Dataset","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.11493","title":"A parametric activation function based on Wendland RBF","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2509.23085","title":"Beyond Gaussian Initializations: Signal Preserving Weight Initialization for Odd-Sigmoid Activations","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2602.10949","title":"Optimal Initialization in Depth: Lyapunov Initialization and Limit Theorems for Deep Leaky ReLU Networks","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.05204","title":"Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.11639","title":"Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.02591","title":"Universal Smoothness via Bernstein Polynomials: A Constructive Approximation Approach for Activation Functions","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.11558","title":"A Composite Activation Function for Learning Stable Binary Representations","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.21648","title":"Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.08218","title":"How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.03148","title":"Rethinking Neural Nonlinearity as Gating","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.03825","title":"Q-TriM: Question-Guided Tri-Modal Attention for Audio-Visual Question Answering","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2609.09244","title":"Critical initialization destabilizes higher input derivatives in wide scalar-input networks","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.30633","title":"Stable initialization without the CLT","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}