Skip to yearly menu bar Skip to main content


Timezone: CET
Filter Events
Poster
10:00 AM - 11:30 AM
92 Events in this session
Marco Rando · Luigi Carratino · Silvia Villa · Lorenzo Rosasco
Matteo Gamba · Adrian Chmielewski-Anders · Josephine Sullivan · Hossein Azizpour · Marten Bjorkman
Chieh Wu · Aria Masoomi · Arthur Gretton · Jennifer Dy
Yeshu Li · Zhan Shi · Xinhua Zhang · Brian Ziebart
Luis Antonio Ortega Andrés · Rafael Cabañas · Andres Masegosa
Dorian Baudry · Yoan Russac · Emilie Kaufmann
Harish Doddi · Deepjyoti Deka · Saurav Talukdar · Murti Salapaka
Ruo-Chun Tzeng · Po-An Wang · Florian Adriaens · Aristides Gionis · Chi-Jen Lu
Jean Ruppert · Marharyta Aleksandrova · Thomas Engel
Marcelo Hartmann · Mark Girolami · Arto Klami
Nguyen Thanh · Trung Le · He Zhao · Jianfei Cai · Dinh Phung
Tam Le · Truyen Nguyen · Dinh Phung · Viet Anh Nguyen
Xuhui Zhang · Jose Blanchet · Soumyadip Ghosh · Mark Squillante
Pierre Laforgue · Giulia Clerici · Nicolò Cesa-Bianchi · Ran Gilad-Bachrach
Antoine Barrier · Aurélien Garivier · Tomáš Kocák
Adil Salim · Laurent CONDAT · Dmitry Kovalev · Peter Richtarik
Jonas Kübler · Wittawat Jitkrittum · Bernhard Schölkopf · Krikamol Muandet
Xun Qian · Rustem Islamov · Mher Safaryan · Peter Richtarik
Agustinus Kristiadi · Matthias Hein · Philipp Hennig
Zhenlin Wang · Andrew Wagenmaker · Kevin Jamieson
Danny Wood · Tingting Mu · Gavin Brown
Arne Nix · Suhas Shrinivasan · Edgar Walker · Fabian Sinz
Ehsan Mokhtarian · Fateme Jamshidi · Jalal Etesami · Negar Kiyavash
Ben Barrett · Alexander Camuto · Matthew Willetts · Tom Rainforth
Ana Lucic · Maartje ter Hoeve · Gabriele Tolomei · Maarten de Rijke · Fabrizio Silvestri
Jonathan Lorraine · David Acuna · Paul Vicol · David Duvenaud
Xuezhou Zhang · Yiding Chen · Xiaojin Zhu · Wen Sun
XINLEI XU · Awni Hannun · Laurens van der Maaten
Marius Memmel · Puze Liu · Davide Tateo · Jan Peters
Benjamin Lengerich · Eric Xing · Rich Caruana
Paulina Tomaszewska · Adam Żychowski · Jacek Mańdziuk
Evrard Garcelon · Matteo Pirotta · Vianney Perchet
Feras Saad · Marco Cusumano-Towner · Vikash Mansinghka
Xiaolu Wang · Peng Wang · Anthony Man-Cho So
Isaac Sebenius · Topi Paananen · Aki Vehtari
Michail Fasoulakis · Evangelos Markakis · Yannis Pantazis · Constantinos Varsos
Vidhi Lalchand · Aditya Ravuri · Neil Lawrence
Sela Fried · Geoffrey Wolfer
Piyushi Manupriya · Tarun Menta · SakethaNath Jagarlapudi · Vineeth N Balasubramanian
Jordan Ash · Surbhi Goel · Akshay Krishnamurthy · Dipendra Misra
Louis Faury · Marc Abeille · Kwang-Sung Jun · Clement Calauzenes
Hossein Esfandiari · Vahab Mirrokni · Umar Syed · Sergei Vassilvtiskii
Samuel Deng · Yilin Guo · Daniel Hsu · Debmalya Mandal
Moritz Hoffmann · Tanya Braun · Ralf Möller
Ehsan Amid · Rohan Anil · Manfred Warmuth
Antoine Chatalic · Luigi Carratino · Ernesto De Vito · Lorenzo Rosasco
Amit Peleg · Naama Pearl · Ron Meir
Yassir Jedra · Alexandre Proutiere
Hiroaki Sasaki · Jun-ichiro Hirayama · Takafumi Kanamori
Alexander Bartler · Andre Bühler · Felix Wiewel · Mario Döbler · Bin Yang
Murad Tukan · Xuan Wu · Samson Zhou · Vladimir Braverman · Dan Feldman
Shiji Zhou · Han Zhao · Shanghang Zhang · Lianzhe Wang · Heng Chang · Zhi Wang · Wenwu Zhu
Khang Le · Huy Nguyen · Khai Nguyen · Tung Pham · Nhat Ho
Matthäus Kleindessner · Samira Samadi · Muhammad Bilal Zafar · Krishnaram Kenthapadi · Chris Russell
Nathanael Bosch · Filip Tronarp · Philipp Hennig
Futoshi Futami · Tomoharu Iwata · Naonori Ueda · Issei Sato · Masashi Sugiyama
Edwige Cyffers · Aurélien Bellet
Fedor Pavutnitskiy · Sergei O. Ivanov · Evgeniy Abramov · Viacheslav Borovitskiy · Artem Klochkov · Viktor Vialov · Anatolii Zaikovskii · Aleksandr Petiushko
QIN DING · Cho-Jui Hsieh · James Sharpnack
Matthew Holland · El Mehdi Haress
Evrard Garcelon · Vashist Avadhanula · Alessandro Lazaric · Matteo Pirotta
Petru Tighineanu · Kathrin Skubch · Paul Baireuther · Attila Reiss · Felix Berkenkamp · Julia Vinogradska
Go to Event Page
Oral
4 Events in this session
Jia-Jie Zhu · Christina Kouridi · Yassine Nemmour · Bernhard Schölkopf
Tianyi Chen · Yuejiao Sun · Quan Xiao · Wotao Yin
Emilien Dupont · Yee Whye Teh · Arnaud Doucet
Go to Event Page
Oral
4 Events in this session
Saeid Naderiparizi · Adam Scibior · Andreas Munk · Mehrdad Ghadiri · Atilim Gunes Baydin · Bradley Gram-Hansen · Christian Schroeder de Witt · Robert Zinkov · Philip Torr · Tom Rainforth · Yee Whye Teh · Frank Wood
Alex Nowak · Alessandro Rudi · Francis Bach
Go to Event Page
Affinity Event

Affinity Group Supported Pathways to ML Research Panel and Social

Maria Skoularidou · Johan Obando Ceron · Pablo Samuel Castro · Sarah Tan · Ezinne Nwankwo · Sanae Lotfi
2:30 PM - 4:00 PM

Ezinne Nwanko (UC Berkeley), Sanae Lofti (New York University), Maria Skoularidou (University of Cambridge), and Johan Obando Cerón (Mila, University of Montreal) will discuss their career paths and how their respective affinity groups helped them along their journey in a panel moderated by Pablo Samuel Castro (Google Brain). The panel is followed by an open social for AISTATS attendees hosted by Sarah Tan (Meta).

... more
Invited Talk

Climate simulations remain our best tools to predict global and regional climate change. Climate projection uncertainty stem, in part, from the poor or lacking representation of processes, such as turbulence, clouds that are not resolved on the grid of global climate models. The representation of these unresolved processes has been a bottleneck in improving climate projections. The explosion of climate data and the power of machine learning algorithms are suddenly offering new opportunities. For example, can data-driven machine learning methods help us deepen our understanding of these unresolved processes and simultaneously improve their representation in climate models to reduce climate projections uncertainty? In this talk, I will discuss the current state of climate modeling and its future, focusing on the advantages and challenges of using machine learning for climate projections. I will present some of our recent work in which we leverage tools from machine learning and deep learning to learn representations of unresolved ocean processes and improve climate simulations. Our work suggests that machine learning could open the door to discovering new physics from data and enhance climate predictions. Yet, many questions remain unanswered, making the next decade exciting and challenging for hybrid climate modeling.

... more
Speaker Bio
Laure Zanna
Laure Zanna is a Professor in Mathematics & Atmosphere/Ocean Science at the Courant Institute, New York University. Her research focuses on the dynamics of the climate system and the main emphasis of her work is to study the influence of the ocean on local and global scales. Prior to NYU, she was a faculty member at the University of Oxford until 2019, and obtained her PhD in 2009 in Climate Dynamics from Harvard University. She was the recipient of the 2020 Nicholas P. Fofonoff Award from the American Meteorological Society “For exceptional creativity in the development and application of new concepts in ocean and climate dynamics”. She is the lead principal investigator of the NSF-NOAA Climate Process Team on Ocean Transport and Eddy Energy, and M2LInES – an international effort to improve climate models with scientific machine learning. She currently serves as an editor for the Journal of Climate, a member on the International CLIVAR Ocean Model Development Panel, and on the CESM Advisory Board.
... more
Oral
4 Events in this session
Kristy Choi · Chenlin Meng · Yang Song · Stefano Ermon
Go to Event Page
Award

Award Ceremony

Gustau Camps-Valls · Francisco Ruiz · Isabel Valera
6:45 PM - 7:00 PM
Test Of Time

This paper considers additive factorial hidden Markov models, an extension to HMMs where the state factors into multiple independent chains, and the output is an additive function of all the hidden states. Although such models are very powerful, accurate inference is unfortunately difficult: exact inference is not computationally tractable, and existing approximate inference techniques are highly susceptible to local optima. In this paper we propose an alternative inference method for such models, which exploits their additive structure by 1) looking at the observed difference signal of the observation, 2) incorporating a “robust” mixture component that can account for unmodeled observations, and 3) constraining the posterior to allow at most one hidden state to change at a time. Combining these elements we develop a convex formulation of approximate inference that is computationally efficient, has no issues of local optima, and which performs much better than existing approaches in practice. The method is motivated by the problem of energy disaggregation, the task of taking a whole home electricity signal and decomposing it into its component appliances; applied to this task, our algorithm achieves state-of-the-art performance, and is able to separate many appliances almost perfectly using just the total aggregate signal.

... more
Affinity Event

WiML - CWS Social

Jessica Kohlschmidt · Christina Papadimitriou · Tatjana Chavdarova
8:00 PM - 9:00 PM

Women in Machine Learning (WiML) and the Caucus for Women in Statistics (CWS) welcome AISTATS attendees to this social event. The event will start with icebreakers to encourage networking among participants. In the main part of the event there will be a Q&A with WiML sponsors, WiML board members and CWS board members in an open format: participants are encouraged to come with questions on various topics ranging from career advice or time-management to conducting research. The event is hosted by Tatjana Chavdarova (UC Berkeley), Christina Papadimitriou (Palo Alto Networks), and Jessica Kohlschmidt (Ohio State University Comprehensive Cancer Center).

... more