Adithya M. Devraj

32 papers A* 2A 1C 4Journal 18Unranked 7

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs. ACL (1) Nicholas E. Corrado, Julian Katz-Samuels, Adithya M. Devraj, Hyokun Yun, Chao Zhang, Yi Xu, Yi Pan, Bing Yin, Trishul Chilimbi
2025	J	`jnl`	AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs. CoRR Nicholas E. Corrado, Julian Katz-Samuels, Adithya M. Devraj, Hyokun Yun, Chao Zhang, Yi Xu, Yi Pan, Bing Yin, Trishul Chilimbi
2022	J	`jnl`	Gaussian Imagination in Bandit Learning. CoRR Yueyang Liu, Adithya M. Devraj, Benjamin Van Roy, Kuang Xu
2022	J	`jnl`	Q-Learning With Uniformly Bounded Variance. IEEE Trans. Autom. Control. Adithya M. Devraj, Sean P. Meyn
2021	J	`jnl`	A Bit Better? Quantifying Information for Bandit Learning. CoRR Adithya M. Devraj, Benjamin Van Roy, Kuang Xu
2021	C	`conf`	Accelerating Optimization and Reinforcement Learning with Quasi Stochastic Approximation. ACC Shuhang Chen, Adithya M. Devraj, Andrey Bernstein, Sean P. Meyn
2021	J	`jnl`	Differential Temporal Difference Learning. IEEE Trans. Autom. Control. Adithya M. Devraj, Ioannis Kontoyiannis, Sean P. Meyn
2021	J	`jnl`	Revisiting the ODE Method for Recursive Algorithms: Fast Convergence Using Quasi Stochastic Approximation. J. Syst. Sci. Complex. Shuhang Chen, Adithya M. Devraj, Andrey Berstein, Sean P. Meyn
2021	J	`jnl`	The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning. CoRR Vivek S. Borkar, Shuhang Chen, Adithya M. Devraj, Ioannis Kontoyiannis, Sean P. Meyn
2020	J	`jnl`	Accelerating Optimization and Reinforcement Learning with Quasi-Stochastic Approximation. CoRR Shuhang Chen, Adithya M. Devraj, Andrey Bernstein, Sean P. Meyn
2020	A	`conf`	Explicit Mean-Square Error Bounds for Monte-Carlo and Linear Stochastic Approximation. AISTATS Shuhang Chen, Adithya M. Devraj, Ana Busic, Sean P. Meyn
2020	J	`jnl`	Explicit Mean-Square Error Bounds for Monte-Carlo and Linear Stochastic Approximation. CoRR Shuhang Chen, Adithya M. Devraj, Ana Busic, Sean P. Meyn
2020	C	`conf`	Model-Free Primal-Dual Methods for Network Optimization with Application to Real-Time Optimal Power Flow. ACC Yue Chen, Andrey Bernstein, Adithya M. Devraj, Sean P. Meyn
2020	J	`jnl`	Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning. CoRR Adithya M. Devraj, Sean P. Meyn
2020	C	`conf`	Reinforcement Learning for Control of Building HVAC Systems. ACC Naren Srivaths Raman, Adithya M. Devraj, Prabir Barooah, Sean P. Meyn
2020	A*	`conf`	Zap Q-Learning With Nonlinear Function Approximation. NeurIPS Shuhang Chen, Adithya M. Devraj, Fan Lu, Ana Busic, Sean P. Meyn
2020	C	`conf`	Zap Q-Learning for Optimal Stopping. ACC Shuhang Chen, Adithya M. Devraj, Ana Busic, Sean P. Meyn
2019	J	`jnl`	Model-Free Primal-Dual Methods for Network Optimization with Application to Real-Time Optimal Power Flow. CoRR Yue Chen, Andrey Bernstein, Adithya M. Devraj, Sean P. Meyn
2019	—	`conf`	On Matrix Momentum Stochastic Approximation and Applications to Q-learning. Allerton Adithya M. Devraj, Ana Busic, Sean P. Meyn
2019	A*	`conf`	Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization. NeurIPS Adithya M. Devraj, Jianshu Chen
2019	J	`jnl`	Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization. CoRR Adithya M. Devraj, Jianshu Chen
2019	J	`jnl`	Zap Q-Learning With Nonlinear Function Approximation. CoRR Shuhang Chen, Adithya M. Devraj, Ana Busic, Sean P. Meyn
2019	J	`jnl`	Zap~Q-Learning for Optimal Stopping Time Problems. CoRR Shuhang Chen, Adithya M. Devraj, Ana Busic, Sean P. Meyn
2018	J	`jnl`	Differential Temporal Difference Learning. CoRR Adithya M. Devraj, Ioannis Kontoyiannis, Sean P. Meyn
2018	J	`jnl`	Zap Meets Momentum: Stochastic Approximation Algorithms with Optimal Convergence Rate. CoRR Adithya M. Devraj, Ana Busic, Sean P. Meyn
2017	J	`jnl`	Fastest Convergence for Q-learning. CoRR Adithya M. Devraj, Sean P. Meyn
2017	—	`conf`	Zap Q-Learning. NIPS Adithya M. Devraj, Sean P. Meyn
2016	J	`jnl`	Differential TD Learning for Value Function Approximation. CoRR Adithya M. Devraj, Sean P. Meyn
2016	—	`conf`	Differential TD learning for value function approximation. CDC Adithya M. Devraj, Sean P. Meyn
2016	—	`conf`	Learning techniques for feedback particle filter design. CDC Anand Radhakrishnan, Adithya M. Devraj, Sean P. Meyn
2015	—	`conf`	Array processing with known waveform and steering vector but unknown diagonal noise covariance matrix. CAMSAP Adithya M. Devraj, Chris Gianelli, Jian Li
2014	—	`conf`	Power allocation in energy harvesting sensors with ARQ: A convex optimization approach. GlobalSIP Adithya M. Devraj, Mohit K. Sharma, Chandra R. Murthy