Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Donti, Priya"'
Autor:
Chai, Sheng, Chadney, Gus, Avery, Charlot, Grunewald, Phil, Van Hentenryck, Pascal, Donti, Priya L.
Access to granular demand data is essential for the net zero transition; it allows for accurate profiling and active demand management as our reliance on variable renewable generation increases. However, public release of this data is often impossibl
Externí odkaz:
http://arxiv.org/abs/2407.11785
We present $\varepsilon$-retrain, an exploration strategy designed to encourage a behavioral preference while optimizing policies with monotonic improvement guarantees. To this end, we introduce an iterative procedure for collecting retrain areas --
Externí odkaz:
http://arxiv.org/abs/2406.08315
Autor:
Rolnick, David, Aspuru-Guzik, Alan, Beery, Sara, Dilkina, Bistra, Donti, Priya L., Ghassemi, Marzyeh, Kerner, Hannah, Monteleoni, Claire, Rolf, Esther, Tambe, Milind, White, Adam
As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly important. Such work offers the potential for significant impact not merely in domains of application but also
Externí odkaz:
http://arxiv.org/abs/2403.17381
Autor:
Batarseh, Feras A., Donti, Priya L., Drgoňa, Ján, Fletcher, Kristen, Hanania, Pierre-Adrien, Hatton, Melissa, Keshav, Srinivasan, Knowles, Bran, Kotsch, Raphaela, McGinnis, Sean, Mitra, Peetak, Philp, Alex, Spohrer, Jim, Stein, Frank, Tare, Meghna, Volkov, Svitlana, Wen, Gege
Climate change is one of the most pressing challenges of our time, requiring rapid action across society. As artificial intelligence tools (AI) are rapidly deployed, it is therefore crucial to understand how they will impact climate action. On the on
Externí odkaz:
http://arxiv.org/abs/2212.13631
In recent years, the ML community has seen surges of interest in both adversarially robust learning and implicit layers, but connections between these two areas have seldom been explored. In this work, we combine innovations from these areas to tackl
Externí odkaz:
http://arxiv.org/abs/2111.06961
While reinforcement learning (RL) is gaining popularity in energy systems control, its real-world applications are limited due to the fact that the actions from learned policies may not satisfy functional requirements or be feasible for the underlyin
Externí odkaz:
http://arxiv.org/abs/2105.08881
Publikováno v:
International Conference on Learning Representations 2021
Large optimization problems with hard constraints arise in many settings, yet classical solvers are often prohibitively slow, motivating the use of deep networks as cheap "approximate solvers." Unfortunately, naive deep learning approaches typically
Externí odkaz:
http://arxiv.org/abs/2104.12225
Publikováno v:
International Conference on Learning Representations 2021
When designing controllers for safety-critical systems, practitioners often face a challenging tradeoff between robustness and performance. While robust control methods provide rigorous guarantees on system stability under certain worst-case disturba
Externí odkaz:
http://arxiv.org/abs/2011.08105
Autor:
Rolnick, David, Donti, Priya L., Kaack, Lynn H., Kochanski, Kelly, Lacoste, Alexandre, Sankaran, Kris, Ross, Andrew Slavin, Milojevic-Dupont, Nikola, Jaques, Natasha, Waldman-Brown, Anna, Luccioni, Alexandra, Maharaj, Tegan, Sherwin, Evan D., Mukkavilli, S. Karthik, Kording, Konrad P., Gomes, Carla, Ng, Andrew Y., Hassabis, Demis, Platt, John C., Creutzig, Felix, Chayes, Jennifer, Bengio, Yoshua
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society a
Externí odkaz:
http://arxiv.org/abs/1906.05433
Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introducing a differentiable (smoothed) maximum satisfiability (MAXSAT) solver
Externí odkaz:
http://arxiv.org/abs/1905.12149