
Fundamental Limits and Tradeoffs in Invariant Representation Learning
Many machine learning applications involve learning representations that...
read it

Invariant Rationalization
Selective rationalization improves neural network interpretability by id...
read it

Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces
This paper focuses on the problem of unsupervised alignment of hierarchi...
read it

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control
Selective rationalization has become a common mechanism to ensure that p...
read it

A Game Theoretic Approach to Classwise Selective Rationalization
Selection of input features such as relevant pieces of text has become a...
read it

Learning to Make Generalizable and Diverse Predictions for Retrosynthesis
We propose a new model for making generalizable and diverse retrosynthet...
read it

Locally Constant Networks
We show how neural models can be used to realize piecewise constant fun...
read it

Towards Robust, Locally Linear Deep Networks
Deep networks realize complex mappings that are often understood by thei...
read it

A Stratified Approach to Robustness for Randomly Smoothed Classifiers
Strong theoretical guarantees of robustness can be given for ensembles o...
read it

Functional Transparency for Structured Data: a GameTheoretic Approach
We provide a new approach to training neural models to exhibit transpare...
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...
read it

GromovWasserstein Alignment of Word Embedding Spaces
Crosslingual or crossdomain correspondences play key roles in tasks ra...
read it

GameTheoretic Interpretability for Temporal Modeling
Interpretability has arisen as a key desideratum of machine learning mod...
read it

Towards Optimal Transport with Global Invariances
Many problems in machine learning involve calculating correspondences be...
read it

On the Robustness of Interpretability Methods
We argue that robustness of explanationsi.e., that similar inputs sho...
read it

Towards Robust Interpretability with SelfExplaining Neural Networks
Most recent work on interpretability of complex machine learning models ...
read it

Structured Optimal Transport
Optimal Transport has recently gained interest in machine learning for a...
read it

From random walks to distances on unweighted graphs
Large unweighted directed graphs are commonly used to capture relations ...
read it

Word, graph and manifold embedding from Markov processes
Continuous vector representations of words and objects appear to carry s...
read it

Metric recovery from directed unweighted graphs
We analyze directed, unweighted graphs obtained from x_i∈R^d by connecti...
read it

Inverse Covariance Estimation for HighDimensional Data in Linear Time and Space: Spectral Methods for Riccati and Sparse Models
We propose maximum likelihood estimation for learning Gaussian graphical...
read it

Computing Upper and Lower Bounds on Likelihoods in Intractable Networks
We present deterministic techniques for computing upper and lower bounds...
read it

Tractable Bayesian Learning of Tree Belief Networks
In this paper we present decomposable priors, a family of priors over st...
read it

Feature Selection and Dualities in Maximum Entropy Discrimination
Incorporating feature selection into a classification or regression meth...
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...
read it

Unsupervised Active Learning in Large Domains
Active learning is a powerful approach to analyzing data effectively. We...
read it

Continuation Methods for Mixing Heterogenous Sources
A number of modern learning tasks involve estimation from heterogeneous ...
read it

On Information Regularization
We formulate a principle for classification with the knowledge of the ma...
read it

Convergent Propagation Algorithms via Oriented Trees
Inference problems in graphical models are often approximated by casting...
read it

Tightening LP Relaxations for MAP using Message Passing
Linear Programming (LP) relaxations have become powerful tools for findi...
read it
Tommi S. Jaakkola
is this you? claim profile
Professor of Electrical Engineering and Computer Science and the Institute for Data, Systems, and Society.