no code implementations • 2 Apr 2024 • Johnny Xi, Jason Hartford
Multimodal representation learning techniques typically rely on paired samples to learn common representations, but paired samples are challenging to collect in fields such as biology where measurement devices often destroy the samples.
1 code implementation • 29 Oct 2023 • Amin Mansouri, Jason Hartford, Yan Zhang, Yoshua Bengio
Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees (up to some reasonable equivalence class).
1 code implementation • 11 Feb 2023 • Elisabeth Ailer, Jason Hartford, Niki Kilbertus
Instrumental variable (IV) methods are used to estimate causal effects in settings with unobserved confounding, where we cannot directly experiment on the treatment variable.
1 code implementation • NeurIPS 2023 • Lazar Atanackovic, Alexander Tong, Bo wang, Leo J. Lee, Yoshua Bengio, Jason Hartford
In this paper we leverage the fact that it is possible to estimate the "velocity" of gene expression with RNA velocity techniques to develop an approach that addresses both challenges.
no code implementations • 1 Feb 2023 • Moksh Jain, Tristan Deleu, Jason Hartford, Cheng-Hao Liu, Alex Hernandez-Garcia, Yoshua Bengio
However, in order to truly leverage large-scale data sets and high-throughput experimental setups, machine learning methods will need to be further improved and better integrated in the scientific discovery pipeline.
1 code implementation • 22 Nov 2022 • Chris Cameron, Jason Hartford, Taylor Lundy, Tuan Truong, Alan Milligan, Rex Chen, Kevin Leyton-Brown
We introduce Monte Carlo Forest Search (MCFS), a class of reinforcement learning (RL) algorithms for learning policies in {tree MDPs}, for which policy execution involves traversing an exponential-sized tree.
1 code implementation • 2 Jun 2022 • Kartik Ahuja, Jason Hartford, Yoshua Bengio
We show that if the perturbations are applied only on mutually exclusive blocks of latents, we identify the latents up to those blocks.
no code implementations • ICLR 2022 • Kartik Ahuja, Jason Hartford, Yoshua Bengio
These results suggest that by exploiting inductive biases on mechanisms, it is possible to design a range of new identifiable representation learning approaches.
no code implementations • 18 Jun 2021 • Chris Cameron, Jason Hartford, Taylor Lundy, Kevin Leyton-Brown
Typically, learning the prediction model used to generate the optimization problem and solving that problem are performed in two separate stages.
no code implementations • NeurIPS 2020 • Jason Hartford, Kevin Leyton-Brown, Hadas Raviv, Dan Padnos, Shahar Lev, Barak Lenz
The challenge is that we are not informed which labels are common and which are rare, and the true label distribution may exhibit extreme skew.
no code implementations • 19 Jun 2020 • Jason Hartford, Victor Veitch, Dhanya Sridhar, Kevin Leyton-Brown
The technique is simple to apply and is "black-box" in the sense that it may be used with any instrumental variable estimator as long as the treatment effect is identified for each valid instrument independently.
1 code implementation • ICML 2018 • Jason Hartford, Devon R Graham, Kevin Leyton-Brown, Siamak Ravanbakhsh
In experiments, our models achieved surprisingly good generalization performance on this matrix extrapolation task, both within domains (e. g., new users and new movies drawn from the same distribution used for training) and even across domains (e. g., predicting music ratings after training on movies).
Ranked #3 on Recommendation Systems on YahooMusic Monti
1 code implementation • ICML 2017 • Jason Hartford, Greg Lewis, Kevin Leyton-Brown, Matt Taddy
Counterfactual prediction requires understanding causal relationships between so-called treatment and outcome variables.
no code implementations • 30 Dec 2016 • Jason Hartford, Greg Lewis, Kevin Leyton-Brown, Matt Taddy
We are in the middle of a remarkable rise in the use and capability of artificial intelligence.