Tommi S. Jaakkola

is this you? claim profile

0 followers
MIT

Professor of Electrical Engineering and Computer Science and the Institute for Data, Systems, and Society.

Fundamental Limits and Tradeoffs in Invariant Representation Learning

Many machine learning applications involve learning representations that...
12/19/2020 ∙ by Han Zhao, et al. ∙ 0 ∙ share

read it
Invariant Rationalization

Selective rationalization improves neural network interpretability by id...
03/22/2020 ∙ by Shiyu Chang, et al. ∙ 5 ∙ share

read it
Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces

This paper focuses on the problem of unsupervised alignment of hierarchi...
11/06/2019 ∙ by David Alvarez-Melis, et al. ∙ 0 ∙ share

read it
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control

Selective rationalization has become a common mechanism to ensure that p...
10/29/2019 ∙ by Mo Yu, et al. ∙ 0 ∙ share

read it
A Game Theoretic Approach to Class-wise Selective Rationalization

Selection of input features such as relevant pieces of text has become a...
10/28/2019 ∙ by Shiyu Chang, et al. ∙ 13 ∙ share

read it
Learning to Make Generalizable and Diverse Predictions for Retrosynthesis

We propose a new model for making generalizable and diverse retrosynthet...
10/21/2019 ∙ by Benson Chen, et al. ∙ 9 ∙ share

read it
Locally Constant Networks

We show how neural models can be used to realize piece-wise constant fun...
09/30/2019 ∙ by Guang-He Lee, et al. ∙ 0 ∙ share

read it
Towards Robust, Locally Linear Deep Networks

Deep networks realize complex mappings that are often understood by thei...
07/07/2019 ∙ by Guang-He Lee, et al. ∙ 2 ∙ share

read it
A Stratified Approach to Robustness for Randomly Smoothed Classifiers

Strong theoretical guarantees of robustness can be given for ensembles o...
06/12/2019 ∙ by Guang-He Lee, et al. ∙ 1 ∙ share

read it
Functional Transparency for Structured Data: a Game-Theoretic Approach

We provide a new approach to training neural models to exhibit transpare...
02/26/2019 ∙ by Guang-He Lee, et al. ∙ 0 ∙ share

read it
Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling

We consider the problem of inferring the values of an arbitrary set of v...
02/06/2019 ∙ by Hao Wang, et al. ∙ 24 ∙ share

read it
Gromov-Wasserstein Alignment of Word Embedding Spaces

Cross-lingual or cross-domain correspondences play key roles in tasks ra...
08/31/2018 ∙ by David Alvarez-Melis, et al. ∙ 0 ∙ share

read it
Game-Theoretic Interpretability for Temporal Modeling

Interpretability has arisen as a key desideratum of machine learning mod...
06/30/2018 ∙ by Guang-He Lee, et al. ∙ 0 ∙ share

read it
Towards Optimal Transport with Global Invariances

Many problems in machine learning involve calculating correspondences be...
06/25/2018 ∙ by David Alvarez-Melis, et al. ∙ 0 ∙ share

read it
On the Robustness of Interpretability Methods

We argue that robustness of explanations---i.e., that similar inputs sho...
06/21/2018 ∙ by David Alvarez-Melis, et al. ∙ 0 ∙ share

read it
Towards Robust Interpretability with Self-Explaining Neural Networks

Most recent work on interpretability of complex machine learning models ...
06/20/2018 ∙ by David Alvarez-Melis, et al. ∙ 0 ∙ share

read it
Structured Optimal Transport

Optimal Transport has recently gained interest in machine learning for a...
12/17/2017 ∙ by David Alvarez-Melis, et al. ∙ 0 ∙ share

read it
From random walks to distances on unweighted graphs

Large unweighted directed graphs are commonly used to capture relations ...
11/02/2015 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Word, graph and manifold embedding from Markov processes

Continuous vector representations of words and objects appear to carry s...
09/18/2015 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Metric recovery from directed unweighted graphs

We analyze directed, unweighted graphs obtained from x_i∈R^d by connecti...
11/20/2014 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Inverse Covariance Estimation for High-Dimensional Data in Linear Time and Space: Spectral Methods for Riccati and Sparse Models

We propose maximum likelihood estimation for learning Gaussian graphical...
09/26/2013 ∙ by Jean Honorio, et al. ∙ 0 ∙ share

read it
Computing Upper and Lower Bounds on Likelihoods in Intractable Networks

We present deterministic techniques for computing upper and lower bounds...
02/13/2013 ∙ by Tommi S. Jaakkola, et al. ∙ 0 ∙ share

read it
Tractable Bayesian Learning of Tree Belief Networks

In this paper we present decomposable priors, a family of priors over st...
01/16/2013 ∙ by Marina Meila, et al. ∙ 0 ∙ share

read it
Feature Selection and Dualities in Maximum Entropy Discrimination

Incorporating feature selection into a classification or regression meth...
01/16/2013 ∙ by Tony S. Jebara, et al. ∙ 0 ∙ share

read it
A New Class of Upper Bounds on the Log Partition Function

Bounds on the log partition function are important in a variety of conte...
12/12/2012 ∙ by Martin Wainwright, et al. ∙ 0 ∙ share

read it
Unsupervised Active Learning in Large Domains

Active learning is a powerful approach to analyzing data effectively. We...
12/12/2012 ∙ by Harald Steck, et al. ∙ 0 ∙ share

read it
Continuation Methods for Mixing Heterogenous Sources

A number of modern learning tasks involve estimation from heterogeneous ...
12/12/2012 ∙ by Adrian Corduneanu, et al. ∙ 0 ∙ share

read it
On Information Regularization

We formulate a principle for classification with the knowledge of the ma...
10/19/2012 ∙ by Adrian Corduneanu, et al. ∙ 0 ∙ share

read it
Convergent Propagation Algorithms via Oriented Trees

Inference problems in graphical models are often approximated by casting...
06/20/2012 ∙ by Amir Globerson, et al. ∙ 0 ∙ share

read it
Tightening LP Relaxations for MAP using Message Passing

Linear Programming (LP) relaxations have become powerful tools for findi...
06/13/2012 ∙ by David Sontag, et al. ∙ 0 ∙ share

read it

Tommi S. Jaakkola

Featured Co-authors