Search Results - "Poli, Michael"

Learning Stochastic Optimal Policies via Gradient Descent by Massaroli, Stefano, Poli, Michael, Peluchetti, Stefano, Park, Jinkyoo, Yamashita, Atsushi, Asama, Hajime

“…We systematically develop a learning-based treatment of stochastic optimal control (SOC), relying on direct optimization of parametric control policies. We…”
Get full text

Autonomous screening of complex phase spaces using Bayesian optimization for SAXS measurements by Younes, Khaled, Poli, Michael, Muhunthan, Priyanka, Rajkovic, Ivan, Ermon, Stefano, Weiss, Thomas M., Ihme, Matthias

“…The advent of modern, ultrafast X-ray experiments has enabled scientists to probe physical phenomena at an ever smaller scale. However, this has come at a cost…”
Get full text

Autonomous screening of complex phase spaces using Bayesian optimization for SAXS measurements by Younes, Khaled, Poli, Michael, Muhunthan, Priyanka, Rajkovic, Ivan, Ermon, Stefano, Weiss, Thomas M., Ihme, Matthias

“…The advent of modern, ultrafast X-ray experiments has enabled scientists to probe physical phenomena at an ever smaller scale. However, this has come at a cost…”
Get full text

Sequence modeling and design from molecular to genome scale with Evo by Nguyen, Eric, Poli, Michael, Durrant, Matthew G., Kang, Brian, Katrekar, Dhruva, Li, David B., Bartie, Liam J., Thomas, Armin W., King, Samuel H., Brixi, Garyk, Sullivan, Jeremy, Ng, Madelena Y., Lewis, Ashley, Lou, Aaron, Ermon, Stefano, Baccus, Stephen A., Hernandez-Boussard, Tina, Ré, Christopher, Hsu, Patrick D., Hie, Brian L.

“…The genome is a sequence that encodes the DNA, RNA, and proteins that orchestrate an organism’s function. We present Evo, a long-context genomic foundation…”
Get full text

Successful Programs and Strategies for Secondary Students Who Are Gifted and in Mathematics Classes: A Qualitative Study by Poli, Michael David

“…Through interview responses, this study examines the perceptions of seven secondary mathematics teachers concerning the programs and methods they incorporate…”
Get full text

Learning Efficient Surrogate Dynamic Models with Graph Spline Networks by Hua, Chuanbo, Berto, Federico, Poli, Michael, Massaroli, Stefano, Park, Jinkyoo

“…While complex simulations of physical systems have been widely used in engineering and scientific computing, lowering their often prohibitive computational…”
Get full text

Ideal Abstractions for Decision-Focused Learning by Poli, Michael, Massaroli, Stefano, Ermon, Stefano, Wilder, Bryan, Horvitz, Eric

“…We present a methodology for formulating simplifying abstractions in machine learning systems by identifying and harnessing the utility structure of decisions…”
Get full text

Deep Latent State Space Models for Time-Series Generation by Zhou, Linqi, Poli, Michael, Xu, Winnie, Massaroli, Stefano, Ermon, Stefano

“…Methods based on ordinary differential equations (ODEs) are widely used to build generative models of time-series. In addition to high computational overhead…”
Get full text

Zoology: Measuring and Improving Recall in Efficient Language Models by Arora, Simran, Eyuboglu, Sabri, Timalsina, Aman, Johnson, Isys, Poli, Michael, Zou, James, Rudra, Atri, Ré, Christopher

“…Attention-free language models that combine gating and convolutions are growing in popularity due to their efficiency and increasingly competitive performance…”
Get full text

Neural Solvers for Fast and Accurate Numerical Optimal Control by Berto, Federico, Massaroli, Stefano, Poli, Michael, Park, Jinkyoo

“…Synthesizing optimal controllers for dynamical systems often involves solving optimization problems with hard real-time constraints. These constraints…”
Get full text

Effectively Modeling Time Series with Simple Discrete State Spaces by Zhang, Michael, Saab, Khaled K, Poli, Michael, Dao, Tri, Goel, Karan, Ré, Christopher

“…Time series modeling is a well-established problem, which often requires that methods (1) expressively represent complicated dependencies, (2) forecast long…”
Get full text

WATTNet: Learning to Trade FX via Hierarchical Spatio-Temporal Representation of Highly Multivariate Time Series by Poli, Michael, Park, Jinkyoo, Ilievski, Ilija

“…Finance is a particularly challenging application area for deep learning models due to low noise-to-signal ratio, non-stationarity, and partial observability…”
Get full text

Transform Once: Efficient Operator Learning in Frequency Domain by Poli, Michael, Massaroli, Stefano, Berto, Federico, Park, Jinykoo, Dao, Tri, Ré, Christopher, Ermon, Stefano

“…Spectral analysis provides one of the most effective paradigms for information-preserving dimensionality reduction, as simple descriptions of naturally…”
Get full text

Mechanistic Design and Scaling of Hybrid Architectures by Poli, Michael, Thomas, Armin W, Nguyen, Eric, Ponnusamy, Pragaash, Deiseroth, Björn, Kersting, Kristian, Suzuki, Taiji, Hie, Brian, Ermon, Stefano, Ré, Christopher, Zhang, Ce, Massaroli, Stefano

“…The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs…”
Get full text

Project Strategy Matching Project Structure to Project Type to Achieve Better Success by Poli, Michael, Cosic, Ilija, Lalic, Bojan

“…This research looked at a number of real-life projects to determine if a distinct project structure was employed for a specific project type and whether the…”
Get full text

TorchDyn: A Neural Differential Equations Library by Poli, Michael, Massaroli, Stefano, Yamashita, Atsushi, Asama, Hajime, Park, Jinkyoo

“…Continuous-depth learning has recently emerged as a novel perspective on deep learning, improving performance in tasks related to dynamical systems and density…”
Get full text

Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations by Poli, Michael, Xu, Winnie, Massaroli, Stefano, Meng, Chenlin, Kim, Kuno, Ermon, Stefano

“…Many patterns in nature exhibit self-similarity: they can be compactly described via self-referential transformations. Said patterns commonly appear in natural…”
Get full text

Hyena Hierarchy: Towards Larger Convolutional Language Models by Poli, Michael, Massaroli, Stefano, Nguyen, Eric, Fu, Daniel Y, Dao, Tri, Baccus, Stephen, Bengio, Yoshua, Ermon, Stefano, Ré, Christopher

“…Recent advances in deep learning have relied heavily on the use of large Transformers due to their ability to learn at scale. However, the core building block…”
Get full text

Hypersolvers: Toward Fast Continuous-Depth Models by Poli, Michael, Massaroli, Stefano, Yamashita, Atsushi, Asama, Hajime, Park, Jinkyoo

“…The infinite-depth paradigm pioneered by Neural ODEs has launched a renaissance in the search for novel dynamical system-inspired deep learning primitives;…”
Get full text

Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture by Fu, Daniel Y, Arora, Simran, Grogan, Jessica, Johnson, Isys, Eyuboglu, Sabri, Thomas, Armin W, Spector, Benjamin, Poli, Michael, Rudra, Atri, Ré, Christopher

“…Machine learning models are increasingly being scaled in both sequence length and model dimension to reach longer contexts and better performance. However,…”
Get full text