{"list":"other","total":94,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1708.03999","title":"ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models","created":"2017-08-14","cited_by_count":666},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"1311.0776","title":"The Composition Theorem for Differential Privacy","created":"2013-11-04","cited_by_count":297},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"id":"1807.01695","title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","created":"2018-07-04","cited_by_count":287},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266},{"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":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"id":"1812.04754","title":"Gradient Descent Happens in a Tiny Subspace","created":"2018-12-12","cited_by_count":217},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"1908.09970","title":"Private Stochastic Convex Optimization with Optimal Rates","created":"2019-08-27","cited_by_count":186},{"id":"2006.06914","title":"Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses","created":"2020-06-12","cited_by_count":173},{"id":"2005.04763","title":"Private Stochastic Convex Optimization: Optimal Rates in Linear Time","created":"2020-05-10","cited_by_count":153},{"id":"2006.15429","title":"Understanding Gradient Clipping in Private SGD: A Geometric Perspective","created":"2020-06-27","cited_by_count":142},{"id":"1802.05251","title":"Differentially Private Empirical Risk Minimization Revisited: Faster and More General","created":"2018-02-14","cited_by_count":128},{"id":"1507.08752","title":"An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback","created":"2015-07-31","cited_by_count":111},{"id":"1805.10367","title":"Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization","created":"2018-05-25","cited_by_count":111},{"id":"2309.11765","title":"Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation","created":"2023-09-21","cited_by_count":96},{"id":"2007.03813","title":"Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification","created":"2020-07-07","cited_by_count":90},{"id":"2103.01516","title":"Private Stochastic Convex Optimization: Optimal Rates in $\\ell_1$ Geometry","created":"2021-03-02","cited_by_count":83},{"id":"2305.01588","title":"Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees","created":"2023-05-02","cited_by_count":83},{"id":"1810.00068","title":"Differentially Private Contextual Linear Bandits","created":"2018-09-28","cited_by_count":82},{"id":"1910.06513","title":"ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization","created":"2019-10-15","cited_by_count":76},{"id":"2310.02025","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","created":"2023-10-03","cited_by_count":76},{"id":"2202.08587","title":"Gradients without Backpropagation","created":"2022-02-17","cited_by_count":73},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67},{"id":"2210.00038","title":"Differentially Private Optimization on Large Model at Small Cost","created":"2022-09-30","cited_by_count":65},{"id":"1710.10551","title":"Stochastic Zeroth-order Optimization in High Dimensions","created":"2017-10-29","cited_by_count":63},{"id":"1703.09947","title":"Efficient Private ERM for Smooth Objectives","created":"2017-03-29","cited_by_count":61},{"id":"2201.09531","title":"Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning","created":"2022-01-24","cited_by_count":59},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52},{"id":"1804.02395","title":"Structured Evolution with Compact Architectures for Scalable Policy Optimization","created":"2018-04-06","cited_by_count":48},{"id":"2207.00160","title":"When Does Differentially Private Learning Not Suffer in High Dimensions?","created":"2022-07-01","cited_by_count":48},{"id":"1910.12166","title":"Improved Zeroth-Order Variance Reduced Algorithms and Analysis for Nonconvex Optimization","created":"2019-10-27","cited_by_count":47},{"id":"2003.13001","title":"Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling","created":"2020-03-29","cited_by_count":46},{"id":"2211.12485","title":"HyperTuning: Toward Adapting Large Language Models without Back-propagation","created":"2022-11-22","cited_by_count":46},{"id":"1511.08681","title":"Algorithms for Differentially Private Multi-Armed Bandits","created":"2015-11-27","cited_by_count":45},{"id":"2205.12506","title":"Memorization in NLP Fine-tuning Methods","created":"2022-05-25","cited_by_count":45},{"id":"2310.06714","title":"Exploring Memorization in Fine-tuned Language Models","created":"2023-10-10","cited_by_count":45},{"id":"1606.00498","title":"A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order","created":"2016-06-01","cited_by_count":44},{"id":"1911.06317","title":"Gradientless Descent: High-Dimensional Zeroth-Order Optimization","created":"2019-11-14","cited_by_count":43},{"id":"2209.05045","title":"Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization","created":"2022-09-12","cited_by_count":43},{"id":"1808.10101","title":"DP-ADMM: ADMM-based Distributed Learning with Differential Privacy","created":"2018-08-30","cited_by_count":42},{"id":"1809.06474","title":"Zeroth-order Nonconvex Stochastic Optimization: Handling Constraints, High-Dimensionality and Saddle-Points","created":"2018-09-17","cited_by_count":37},{"id":"2302.09483","title":"Why Is Public Pretraining Necessary for Private Model Training?","created":"2023-02-19","cited_by_count":37},{"id":"2206.13033","title":"Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization","created":"2022-06-27","cited_by_count":36},{"id":"2212.09257","title":"PromptBoosting: Black-Box Text Classification with Ten Forward Passes","created":"2022-12-19","cited_by_count":36},{"id":"2206.00846","title":"Faster Rates of Convergence to Stationary Points in Differentially Private Optimization","created":"2022-06-02","cited_by_count":32},{"id":"2006.13501","title":"Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds","created":"2020-06-24","cited_by_count":26},{"id":"2205.13709","title":"DP-PCA: Statistically Optimal and Differentially Private PCA","created":"2022-05-27","cited_by_count":24},{"id":"2206.00363","title":"Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization","created":"2022-06-01","cited_by_count":22},{"id":"2001.07819","title":"Zeroth-Order Algorithms for Nonconvex Minimax Problems with Improved Complexities","created":"2020-01-22","cited_by_count":21},{"id":"2306.03257","title":"Generating Private Synthetic Data with Genetic Algorithms","created":"2023-06-05","cited_by_count":18},{"id":"2306.10015","title":"Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomness","created":"2023-06-16","cited_by_count":18},{"id":"2111.02516","title":"Differential Privacy Over Riemannian Manifolds","created":"2021-11-03","cited_by_count":16},{"id":"2305.13209","title":"Faster Differentially Private Convex Optimization via Second-Order Methods","created":"2023-05-22","cited_by_count":13},{"id":"2309.05505","title":"Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning","created":"2023-09-11","cited_by_count":13},{"id":"2205.09494","title":"Differentially private Riemannian optimization","created":"2022-05-19","cited_by_count":12},{"id":"2302.09699","title":"Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks","created":"2023-02-20","cited_by_count":12},{"id":"2307.05753","title":"Zeroth-order Optimization with Weak Dimension Dependency","created":"2023-07-11","cited_by_count":11},{"id":"2210.06328","title":"Momentum Aggregation for Private Non-convex ERM","created":"2022-10-12","cited_by_count":10},{"id":"2206.01836","title":"Dimension Independent Generalization of DP-SGD for Overparameterized Smooth Convex Optimization","created":"2022-06-03","cited_by_count":9},{"id":"2301.13273","title":"Near Optimal Private and Robust Linear Regression","created":"2023-01-30","cited_by_count":9},{"id":"2208.04245","title":"Differentially Private Fr\\'echet Mean on the Manifold of Symmetric Positive Definite (SPD) Matrices with log-Euclidean Metric","created":"2022-08-08","cited_by_count":8}],"next_cursor":null}