We consider minimizing functions for which it is expensive to compute the (possibly stochastic) gradient. Such functions are prevalent in reinforcement learning, imitation learning and adversarial training. Our target optimization framework…
Published in CVPR 2023 Workshop-2023, 2023 Recommended citation: Setareh, Dabiri, et al. "Realistically distributing object placements in synthetic training data improves the performance of vision-based object detection models" CVPR 2023 Wo…
Published in IEEE-ITSC-2023, 2023 Recommended citation: Liu, Yunpeng, et al. "Video Killed the HD-Map: Predicting Driving Behavior Directly From Drone Images" IEEE-ITSC 2023. https://arxiv.org/abs/2305.11856 The development of algorithms th…
Recommended citation: Ramesh, Amrutha, et al. "Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm" Arxiv 2023. https://arxiv.org/abs/2307.01169 We consider minimizing…
Published in NuerIPS-2023, 2023 Recommended citation: Niedoba, Matthew, et al. "A Diffusion-Model of Joint Interactive Navigation." NuerIPS 2023. https://openreview.net/pdf?id=2yXExAl0FW Simulation of autonomous vehicle systems requires tha…
Recommended citation: Berend, Zwartsenberg, et al. "Conditional Permutation Invariant Flows." TMLR 2023. https://openreview.net/forum?id=DUsgPi3oCC We present a novel, conditional generative probabilistic model of set-valued data with a tra…
Recommended citation: Kunstner, Frederik, et al. "Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might Be" https://www.proquest.com/openview/da3b1b61b3fd2f0ca38a3418172867d9/1?pq-origsite=…
Recommended citation: Lavington, Jonathan, et al. "Target-based Surrogates for Stochastic Optimization." ICML 2023. https://proceedings.mlr.press/v202/lavington23a/lavington23a.pdf We consider minimizing functions for which it is expensive
Recommended citation: Lioutas, Vasileios, et al. "Critic Sequential Monte Carlo." ICLR 2023. https://openreview.net/pdf?id=ObtGcyKmwna We introduce CriticSMC, a new algorithm for planning as inference built from a composition of sequential
Recommended citation: Liu, Yunpeng, et al. "Vehicle Type Specific Waypoint Generation." IROS 2022. https://ieeexplore.ieee.org/abstract/document/9981421 We develop a generic mechanism for generating vehicle-type specific sequences of waypoi…
Recommended citation: Lavington, Jonathan, et al. "Improved Policy Optimization for Online Imitation Learning." CoLLAs 2022. https://proceedings.mlr.press/v199/lavington22a/lavington22a.pdf We consider online imitation learning (OIL), where…
Recommended citation: Warrington, Andrew, et al. "Robust Asymmetric Learning in POMDPs." ICML 2021. https://proceedings.mlr.press/v139/warrington21a.html Policies for partially observed Markov decision processes can be efficiently learned b…