{"list":"other","total":86,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1811.06128","title":"Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon","created":"2018-11-15","cited_by_count":623},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1703.00443","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","created":"2017-03-01","cited_by_count":599},{"id":"1704.01665","title":"Learning Combinatorial Optimization Algorithms over Graphs","created":"2017-04-05","cited_by_count":561},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"1710.08005","title":"Smart \"Predict, then Optimize\"","created":"2017-10-22","cited_by_count":339},{"id":"1906.01629","title":"Exact Combinatorial Optimization with Graph Convolutional Neural Networks","created":"2019-06-04","cited_by_count":318},{"id":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268},{"id":"1604.04562","title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","created":"2016-04-15","cited_by_count":252},{"id":"2109.09831","title":"SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization","created":"2021-09-20","cited_by_count":230},{"id":"1912.02175","title":"Differentiation of Blackbox Combinatorial Solvers","created":"2019-12-04","cited_by_count":226},{"id":"2103.12828","title":"Learning to Optimize: A Primer and A Benchmark","created":"2021-03-23","cited_by_count":208},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"2012.13349","title":"Solving Mixed Integer Programs Using Neural Networks","created":"2020-12-23","cited_by_count":182},{"id":"1905.12149","title":"SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver","created":"2019-05-29","cited_by_count":173},{"id":"1711.08013","title":"OSQP: An Operator Splitting Solver for Quadratic Programs","created":"2017-11-21","cited_by_count":161},{"id":"2103.16378","title":"End-to-End Constrained Optimization Learning: A Survey","created":"2021-03-30","cited_by_count":157},{"id":"1402.5481","title":"From Predictive to Prescriptive Analytics","created":"2014-02-22","cited_by_count":143},{"id":"2303.08233","title":"NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions","created":"2023-03-14","cited_by_count":135},{"id":"2007.04976","title":"One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control","created":"2020-07-09","cited_by_count":121},{"id":"1906.04859","title":"Reinforcement Learning for Integer Programming: Learning to Cut","created":"2019-06-11","cited_by_count":111},{"id":"1703.04813","title":"Learned Optimizers that Scale and Generalize","created":"2017-03-14","cited_by_count":110},{"id":"1909.09586","title":"Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks","created":"2019-09-12","cited_by_count":103},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"id":"2006.15212","title":"Hybrid Models for Learning to Branch","created":"2020-06-26","cited_by_count":95},{"id":"1401.3492","title":"ParamILS: An Automatic Algorithm Configuration Framework","created":"2014-01-15","cited_by_count":89},{"id":"1911.10092","title":"Smart Predict-and-Optimize for Hard Combinatorial Optimization Problems","created":"2019-11-22","cited_by_count":89},{"id":"2301.08210","title":"Everything is Connected: Graph Neural Networks","created":"2023-01-19","cited_by_count":85},{"id":"1803.10150","title":"Learning to Branch","created":"2018-03-27","cited_by_count":78},{"id":"2002.05120","title":"Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies","created":"2020-02-12","cited_by_count":63},{"id":"2206.13414","title":"Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning","created":"2022-06-27","cited_by_count":61},{"id":"1703.03633","title":"Learning Gradient Descent: Better Generalization and Longer Horizons","created":"2017-03-10","cited_by_count":50},{"id":"1611.06256","title":"Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU","created":"2016-11-18","cited_by_count":48},{"id":"2105.13645","title":"Learning to Select Cuts for Efficient Mixed-Integer Programming","created":"2021-05-28","cited_by_count":48},{"id":"2203.02878","title":"A Survey for Solving Mixed Integer Programming via Machine Learning","created":"2022-03-06","cited_by_count":44},{"id":"2107.10201","title":"Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs","created":"2021-07-21","cited_by_count":43},{"id":"1703.00441","title":"Learning to Optimize Neural Nets","created":"2017-03-01","cited_by_count":41},{"id":"2205.13881","title":"Automated Dynamic Algorithm Configuration","created":"2022-05-27","cited_by_count":39},{"id":"1506.02465","title":"ASlib: A Benchmark Library for Algorithm Selection","created":"2015-06-08","cited_by_count":37},{"id":"2006.05082","title":"Learning to Stop While Learning to Predict","created":"2020-06-09","cited_by_count":31},{"id":"2010.09089","title":"Training Stronger Baselines for Learning to Optimize","created":"2020-10-18","cited_by_count":31},{"id":"2111.04469","title":"Mixed-Integer Optimization with Constraint Learning","created":"2021-11-04","cited_by_count":31},{"id":"2210.16934","title":"Learning to Compare Nodes in Branch and Bound with Graph Neural Networks","created":"2022-10-30","cited_by_count":31},{"id":"2107.10847","title":"Accelerating Quadratic Optimization with Reinforcement Learning","created":"2021-07-22","cited_by_count":30},{"id":"2202.01651","title":"A Survey of Methods for Automated Algorithm Configuration","created":"2022-02-03","cited_by_count":30},{"id":"2205.12374","title":"Learning to Model Editing Processes","created":"2022-05-24","cited_by_count":30},{"id":"2005.10026","title":"Reinforcement Learning for Variable Selection in a Branch and Bound Algorithm","created":"2020-05-20","cited_by_count":29},{"id":"2110.02121","title":"Optimization with Constraint Learning: A Framework and Survey","created":"2021-10-05","cited_by_count":28},{"id":"1911.09461","title":"JANOS: An Integrated Predictive and Prescriptive Modeling Framework","created":"2019-11-21","cited_by_count":27},{"id":"2206.14987","title":"Lookback for Learning to Branch","created":"2022-06-30","cited_by_count":27},{"id":"1806.10897","title":"Deep learning in business analytics and operations research: Models, applications and managerial implications","created":"2018-06-28","cited_by_count":24},{"id":"2206.02568","title":"A Deep Reinforcement Learning Framework For Column Generation","created":"2022-06-03","cited_by_count":22},{"id":"1709.04636","title":"Warmstarting of Model-based Algorithm Configuration","created":"2017-09-14","cited_by_count":17},{"id":"2007.03948","title":"A Study of Learning Search Approximation in Mixed Integer Branch and Bound: Node Selection in SCIP","created":"2020-07-08","cited_by_count":16},{"id":"2203.06578","title":"Symbolic Learning to Optimize: Towards Interpretability and Scalability","created":"2022-03-13","cited_by_count":16},{"id":"1807.05517","title":"Boosting Combinatorial Problem Modeling with Machine Learning","created":"2018-07-15","cited_by_count":15},{"id":"2106.10349","title":"The Perils of Learning Before Optimizing","created":"2021-06-18","cited_by_count":15},{"id":"1804.00846","title":"Learning to Search via Retrospective Imitation","created":"2018-04-03","cited_by_count":14},{"id":"2201.06213","title":"An Improved Reinforcement Learning Algorithm for Learning to Branch","created":"2022-01-17","cited_by_count":14},{"id":"1307.4689","title":"DASH: Dynamic Approach for Switching Heuristics","created":"2013-07-17","cited_by_count":13},{"id":"2112.04906","title":"Enhancing Column Generation by a Machine-Learning-Based Pricing Heuristic for Graph Coloring","created":"2021-12-08","cited_by_count":12},{"id":"2111.06257","title":"Branch and Bound in Mixed Integer Linear Programming Problems: A Survey of Techniques and Trends","created":"2021-11-05","cited_by_count":9},{"id":"2102.09663","title":"Smart Feasibility Pump: Reinforcement Learning for (Mixed) Integer Programming","created":"2021-02-18","cited_by_count":8},{"id":"2211.12443","title":"Learning context-aware adaptive solvers to accelerate quadratic programming","created":"2022-11-22","cited_by_count":7},{"id":"2306.05119","title":"Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework","created":"2023-06-08","cited_by_count":7},{"id":"2204.10834","title":"Learning for Spatial Branching: An Algorithm Selection Approach","created":"2022-04-22","cited_by_count":6},{"id":"2010.09933","title":"Proximal Policy Gradient: PPO with Policy Gradient","created":"2020-10-20","cited_by_count":5},{"id":"2110.11991","title":"A Reinforcement Learning Approach to Parameter Selection for Distributed Optimal Power Flow","created":"2021-10-22","cited_by_count":5},{"id":"2111.11358","title":"A Surrogate Objective Framework for Prediction+Optimization with Soft Constraints","created":"2021-11-22","cited_by_count":2},{"id":"2208.05608","title":"Polynomial Optimization: Enhancing RLT relaxations with Conic Constraints","created":"2022-08-11","cited_by_count":1}],"next_cursor":null}