{"list":"other","total":63,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"id":"2301.11916","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","created":"2023-01-27","cited_by_count":149},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133},{"id":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"1909.12292","title":"Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks","created":"2019-09-26","cited_by_count":121},{"id":"2307.15936","title":"A Theory for Emergence of Complex Skills in Language Models","created":"2023-07-29","cited_by_count":113},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"1810.07896","title":"Solving Linear Programs in the Current Matrix Multiplication Time","created":"2018-10-18","cited_by_count":100},{"id":"1810.12065","title":"On the Convergence Rate of Training Recurrent Neural Networks","created":"2018-10-29","cited_by_count":82},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"1906.03593","title":"Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound","created":"2019-06-09","cited_by_count":59},{"id":"2006.11648","title":"Training (Overparametrized) Neural Networks in Near-Linear Time","created":"2020-06-20","cited_by_count":58},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58},{"id":"2010.05846","title":"A Refined Laser Method and Faster Matrix Multiplication","created":"2020-10-12","cited_by_count":56},{"id":"1905.04447","title":"Solving Empirical Risk Minimization in the Current Matrix Multiplication Time","created":"2019-05-11","cited_by_count":53},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49},{"id":"2102.10707","title":"A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization","created":"2021-02-21","cited_by_count":46},{"id":"2004.07470","title":"Faster Dynamic Matrix Inverse for Faster LPs","created":"2020-04-16","cited_by_count":44},{"id":"1910.11957","title":"A Deterministic Linear Program Solver in Current Matrix Multiplication Time","created":"2019-10-25","cited_by_count":42},{"id":"1905.11675","title":"Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems","created":"2019-05-28","cited_by_count":40},{"id":"2103.07601","title":"Approximating How Single Head Attention Learns","created":"2021-03-13","cited_by_count":38},{"id":"2304.02207","title":"Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models","created":"2023-04-05","cited_by_count":37},{"id":"2002.06668","title":"Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality","created":"2020-02-16","cited_by_count":36},{"id":"2211.06033","title":"A Faster Small Treewidth SDP Solver","created":"2022-11-11","cited_by_count":36},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35},{"id":"2101.08208","title":"Solving SDP Faster: A Robust IPM Framework and Efficient Implementation","created":"2021-01-20","cited_by_count":33},{"id":"2307.02419","title":"In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick","created":"2023-07-05","cited_by_count":32},{"id":"2211.14227","title":"Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing","created":"2022-11-25","cited_by_count":29},{"id":"2211.14407","title":"Faster Algorithm for Structured John Ellipsoid Computation","created":"2022-11-26","cited_by_count":28},{"id":"2009.09829","title":"Generalized Leverage Score Sampling for Neural Networks","created":"2020-09-21","cited_by_count":26},{"id":"1905.11580","title":"A near-optimal algorithm for approximating the John Ellipsoid","created":"2019-05-28","cited_by_count":23},{"id":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22},{"id":"2210.11542","title":"Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance","created":"2022-10-20","cited_by_count":22},{"id":"2210.12468","title":"Discrepancy Minimization in Input-Sparsity Time","created":"2022-10-22","cited_by_count":22},{"id":"2210.10173","title":"Faster Matrix Multiplication via Asymmetric Hashing","created":"2022-10-18","cited_by_count":19},{"id":"2307.08045","title":"Beyond Classical Attention: Quantum Attention for Scalable Computation","created":"2023-07-16","cited_by_count":18},{"id":"2307.01189","title":"Trainable Transformer in Transformer","created":"2023-07-03","cited_by_count":17},{"id":"2307.08352","title":"Zero-th Order Algorithm for Softmax Attention Optimization","created":"2023-07-17","cited_by_count":16},{"id":"2105.05001","title":"FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis","created":"2021-05-11","cited_by_count":13},{"id":"2307.07735","title":"Faster Algorithms for Structured Linear and Kernel Support Vector Machines","created":"2023-07-15","cited_by_count":13},{"id":"2304.03426","title":"Convex Minimization with Integer Minima in $\\widetilde O(n^4)$ Time","created":"2023-04-07","cited_by_count":12},{"id":"1401.7714","title":"Powers of Tensors and Fast Matrix Multiplication","created":"2014-01-30","cited_by_count":11},{"id":"2307.06565","title":"Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification","created":"2023-07-13","cited_by_count":11},{"id":"2111.01898","title":"A high performance fingerprint liveness detection method based on quality related features","created":"2021-11-02","cited_by_count":5},{"id":"2305.08001","title":"Structured and Fast Optimization: The Kronecker SGD Algorithm","created":"2023-05-13","cited_by_count":5}],"next_cursor":null}