What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
Alekh Agarwal mainly investigates Mathematical optimization, Artificial intelligence, Convex optimization, Machine learning and Regret. He has researched Mathematical optimization in several fields, including Regularization, Function approximation and Reinforcement learning. His Online machine learning, Computational learning theory, Instance-based learning and Algorithmic learning theory study, which is part of a larger body of work in Artificial intelligence, is frequently linked to Component, bridging the gap between disciplines.
The Convex optimization study combines topics in areas such as Algorithm design, Model of computation, Convex function and Minimax. His Machine learning research is multidisciplinary, incorporating elements of Classifier and Search algorithm. His Minification research incorporates elements of Algorithm, Least squares and Neural coding.
His most cited work include:
- Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling (905 citations)
- Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions (378 citations)
- Distributed Delayed Stochastic Optimization (275 citations)
What are the main themes of his work throughout his whole career to date?
Alekh Agarwal mostly deals with Artificial intelligence, Mathematical optimization, Reinforcement learning, Machine learning and Regret. His work on Leverage as part of general Artificial intelligence research is frequently linked to Space, Oracle and Baseline, thereby connecting diverse disciplines of science. His work in Mathematical optimization addresses subjects such as Convex optimization, which are connected to disciplines such as Applied mathematics.
In his study, Computation is strongly linked to Theoretical computer science, which falls under the umbrella field of Reinforcement learning. His work carried out in the field of Regret brings together such families of science as Algorithm, Realizability and Combinatorics. His study explores the link between Stochastic optimization and topics such as Convex function that cross with problems in Distributed algorithm.
He most often published in these fields:
- Artificial intelligence (31.68%)
- Mathematical optimization (30.43%)
- Reinforcement learning (24.22%)
What were the highlights of his more recent work (between 2017-2021)?
- Reinforcement learning (24.22%)
- Artificial intelligence (31.68%)
- Machine learning (22.36%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Reinforcement learning, Artificial intelligence, Machine learning, Mathematical optimization and Theoretical computer science. Alekh Agarwal has included themes like State and Bellman equation in his Reinforcement learning study. His work on Leverage as part of general Artificial intelligence research is often related to Baseline, Imitation learning, Weighting and Distribution, thus linking different fields of science.
His Machine learning study integrates concerns from other disciplines, such as Classifier and Face. His Mathematical optimization study frequently draws connections between adjacent fields such as Function approximation. His Theoretical computer science study incorporates themes from Cluster analysis, Decoding methods, Identifiability and Complement.
Between 2017 and 2021, his most popular works were:
- A Reductions Approach to Fair Classification. (171 citations)
- A Reductions Approach to Fair Classification (83 citations)
- Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes (81 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
Artificial intelligence, Mathematical optimization, Reinforcement learning, Machine learning and Markov decision process are his primary areas of study. His work in the fields of Leverage overlaps with other areas such as Bias correction. His Leverage research is multidisciplinary, relying on both Supervised learning, Algorithm design, Regret and Realizability.
The concepts of his Mathematical optimization study are interwoven with issues in Regularization and Softmax function. His work deals with themes such as Gradient descent and Function approximation, which intersect with Reinforcement learning. His work in Machine learning is not limited to one particular discipline; it also encompasses Classifier.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
