Ted Moskovitz
graduate student studying machine learning and neuroscience
About Me
I’m a final-year PhD student studying machine learning and theoretical neuroscience at the Gatsby Computational Neuroscience Unit in London, where I’m fortunate to be advised by Maneesh Sahani and Matt Botvinick. I’m interested in understanding and building intelligence, particularly reasoning, sequential decision-making, and optimization (pre- and post-training) for large-scale models. Previously, I interned at DeepMind, where I worked on constrained reinforcement learning, and Uber AI Labs, where I worked on optimization for large-scale deep learning. I received my MSc in computer science with a specialization in machine learning from Columbia University and did my undergrad at Princeton University, where I majored in neuroscience with minors in computer science and linguistics.
| Google Scholar | CV |
Email: ted@gatsby.ucl.ac.uk
Publications and Preprints
Moskovitz T, Singh A, Strouse D, Sandholm T, Salakhutdinov R, Dragan A, McAleer S (2024). Confronting Reward Model Overoptimization with Constrained RLHF. International Conference on Learning Representations (ICLR) (Spotlight, Top 5% of Submissions) paper | code
Singh A, Chan S, Moskovitz T, Grant E, Saxe A, Hill F (2023). The Transient Nature of Emergent In-context Learning in Transformers. Neural Information Processing Systems (NeurIPS).
Moskovitz T, Hromadka S, Touati A, Borsa D, Sahani M (2023). A State Representation for Diminishing Rewards. Neural Information Processing Systems (NeurIPS). paper | code | website
Moskovitz T, O’Donoghue B, Veeriah V, Flennerhag S, Singh S, Zahavy T (2023). ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs. International Conference on Machine Learning (ICML). paper | website
Moskovitz T, Kao T, Sahani M*, Botvinick M* (2023). Minimum Description Length Control. International Conference on Learning Representations (ICLR). *Equal Contribution. paper
Moskovitz T, Miller K, Sahani M, Botvinick M (2022). A Unified Theory of Dual Process Control. Preprint. paper
Moskovitz T, Arbel M, Parker-Holder J, Pacchiano A (2022). Towards an Understanding of Default Policies in Multitask Policy Optimization. Conference on Artificial Intelligence and Statistics (AISTATS). paper (Best Paper Award Honorable Mention)
Moskovitz T, Wilson SR, Sahani M (2022). A First-Occupancy Representation for Reinforcement Learning. International Conference on Learning Representations (ICLR). paper | code | talk at Cosyne
Moskovitz T, Parker-Holder J, Pacchiano A, Arbel M, Jordan MI (2021). Tactical Optimism and Pessimism for Deep Reinforcement Learning. Neural Information Processing Systems (NeurIPS). paper | code
Moskovitz T*, Arbel M*, Huszar F, Gretton A (2021). Efficient Wasserstein Natural Gradients for Reinforcement Learning. International Conference on Learning Representations (ICLR). *Equal contribution. paper | code
Li WK, Moskovitz T, Kanagawa H, Sahani M (2020). Amortised Learning by Wake-Sleep. International Conference on Machine Learning (ICML). paper | code
Moskovitz T, Wang R, Lan J, Kapoor S, Yosinski J, Rawal A (2019). Learned First-Order Preconditioning. Beyond First Order Methods in ML Workshop, Neural Information Processing Systems. paper
Lindsay G, Moskovitz T, Yang G, Miller K (2019). Do Biologically-Plausible Architectures Produce Biologically-Realistic Models? Conference on Cognitive Computational Neuroscience. paper
Sun M, Li J, Moskovitz T, Lindsay G, Miller K, Dipoppa M, Yang G (2019). Understanding the Functional and Structural Differences Across Excitatory and Inhibitory Neurons. Conference on Cognitive Computational Neuroscience. paper
Moskovitz T, Litwin-Kumar A, Abbott LF (2018). Feedback alignment in deep convolutional networks. Pre-print. paper
Moskovitz T, Roy NA, Pillow JW (2018). A comparison of deep learning and linear-nonlinear cascade models to neural encoding. Preprint. paper
Hsu E, Fowler E, Staudt L, Greenberg M, Moskovitz T, Shattuck DW, Joshi SH (2016). DTI of corticospinal tracts pre- and post-physical therapy in children with cerebral palsy. Proceedings of the Organization of Human Brain Mapping. poster