Browsing by Author "Jaakkola, Tommi S"
Now showing items 2139 of 39

LowRank Tensors for Scoring Dependency Structures
Lei, Tao; Zhang, Yuan; Barzilay, Regina; Jaakkola, Tommi S. (Association for Computational Linguistics, 201406)Accurate scoring of syntactic structures such as headmodifier arcs in dependency parsing typically requires rich, highdimensional feature representations. A small subset of such features is often selected manually. This ... 
Metric recovery from directed unweighted graphs
Hashimoto, Tatsunori Benjamin; Sun, Yi; Jaakkola, Tommi S (PMLR, 201505)We analyze directed, unweighted graphs obtained from x[subscript i] ∈ R[superscript d] by connecting vertex i to j iff x[subscript i] − x[subscript j] < ε(x[subscript i]). Examples of such graphs include knearest neighbor ... 
More data means less inference: A pseudomax approach to structured learning
Sontag, David; Meshi, Ofer; Jaakkola, Tommi S.; Globerson, Amir (Neural Information Processing Systems Foundation, 201012)The problem of learning to predict structured labels is of key importance in many applications. However, for general graph structure both learning and inference in this setting are intractable. Here we show that it is ... 
On dual decomposition and linear programming relaxations for natural language processing
Rush, Alexander Matthew; Sontag, David Alexander; Collins, Michael; Jaakkola, Tommi S. (Association for Computational Linguistics, 201010)This paper introduces dual decomposition as a framework for deriving inference algorithms for NLP problems. The approach relies on standard dynamicprogramming algorithms as oracle solvers for subproblems, together ... 
On measure concentration of random maximum aposteriori perturbations
Orabona, Francesco; Hazan, Tamir; Sarwate, Anand D.; Jaakkola, Tommi S. (Association for Computing Machinery (ACM), 2014)The maximum aposteriori (MAP) perturbation framework has emerged as a useful approach for inference and learning in high dimensional complex models. By maximizing a randomly perturbed potential function, MAP perturbations ... 
On sampling from the Gibbs distribution with random maximum aposteriori perturbations
Hazan, Tamir; Maji, Subhransu; Jaakkola, Tommi S. (Neural Information Processing Systems, 2013)In this paper we describe how MAP inference can be used to sample efficiently from Gibbs distributions. Specifically, we provide means for drawing either approximate or unbiased samples from Gibbs' distributions by introducing ... 
Predicting organic reaction outcomes with weisfeilerlehman network
Jin, Wengong; Coley, Connor Wilson; Barzilay, Regina; Jaakkola, Tommi S (Neural Information Processing Systems Foundation, Inc., 201712)The prediction of organic reaction outcomes is a fundamental problem in computational chemistry. Since a reaction may involve hundreds of atoms, fully exploring the space of possible transformations is intractable. The ... 
Principal differences analysis: Interpretable characterization of differences between distributions
Mueller, Jonas Weylin; Jaakkola, Tommi S (Neural Information Processing Systems Foundation, Inc., 201512)We introduce principal differences analysis (PDA) for analyzing differences between highdimensional distributions. The method operates by finding the projection that maximizes the Wasserstein divergence between the resulting ... 
Rationalizing Neural Predictions
Lei, Tao; Barzilay, Regina; Jaakkola, Tommi S (Association for Computational Linguistics (ACL), 201611)Prediction without justification has limited applicability. As a remedy, we learn to extract pieces of input text as justifications – rationales – that are tailored to be short and coherent, yet sufficient for making the ... 
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control
Yu, Mo; Chang, Shiyu; Zhang, Yang; Jaakkola, Tommi S (Association for Computational Linguistics, 201911)Selective rationalization has become a common mechanism to ensure that predictive models reveal how they use any available features. The selection may be soft or hard, and identifies a subset of input features relevant for ... 
Solving graph compression via optimal transport
Garg, Vikas; Jaakkola, Tommi S (Morgan Kaufmann Publishers, 201912)We propose a new approach to graph compression by appeal to optimal transport. The transport problem is seeded with prior information about node importance, attributes, and edges in the graph. The transport formulation can ... 
Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees
Zhang, Yuan; Lei, Tao; Barzilay, Regina; Jaakkola, Tommi S.; Globerson, Amir (Association for Computational Linguistics, 201406)Much of the recent work on dependency parsing has been focused on solving inherent combinatorial problems associated with rich scoring functions. In contrast, we demonstrate that highly expressive scoring functions can be ... 
Tight certificates of adversarial robustness for randomly smoothed classifiers
Lee, GuangHe; Yuan, Yang; Jaakkola, Tommi S (202002)Strong theoretical guarantees of robustness can be given for ensembles of classifiers generated by input randomization. Specifically, an `2 bounded adversary cannot alter the ensemble prediction generated by an additive ... 
Towards optimal transport with global invariances
Alvarez Melis, David; Jegelka, Stefanie Sabrina; Jaakkola, Tommi S (JMLR, 201902)Many problems in machine learning involve calculating correspondences between sets of objects, such as point clouds or images. Discrete optimal transport provides a natural and successful approach to such tasks whenever ... 
Tree block coordinate descent for map in graphical models
Sontag, David Alexander; Jaakkola, Tommi S. (Journal of Machine Learning Research, 200904)A number of linear programming relaxations have been proposed for finding most likely settings of the variables (MAP) in large probabilistic models. The relaxations are often succinctly expressed in the dual and reduce to ... 
Twosided exponential concentration bounds for Bayes error rate and Shannon entropy
Honorio, Jean; Jaakkola, Tommi S. (Association for Computing Machinery (ACM), 2013)We provide a method that approximates the Bayes error rate and the Shannon entropy with high probability. The Bayes error rate approximation makes possible to build a classifier that polynomially approaches Bayes error ... 
A unified framework for consistency of regularized loss minimizers
Honorio, Jean; Jaakkola, Tommi S. (Association for Computing Machinery (ACM), 2014)We characterize a family of regularized loss minimization problems that satisfy three properties: scaled uniform convergence, supernorm regularization, and normloss monotonicity. We show several theoretical guarantees ... 
An unsupervised method for uncovering morphological chains
Narasimhan, Karthik Rajagopal; Barzilay, Regina; Jaakkola, Tommi S. (Association for Computational Linguistics, 201503)Most stateoftheart systems today produce morphological analysis based only on orthographic patterns. In contrast, we propose a model for unsupervised morphological analysis that integrates orthographic and semantic views ... 
Validation and refinement of generegulatory pathways on a network of physical interactions
Yeang, ChenHsiang, 1969; Mak, Craig; McCuine, Scott; Workman, Christopher; Ideker, Trey; e.a. (BioMed Central Ltd, 200507)As genomescale measurements lead to increasingly complex models of gene regulation, systematic approaches are needed to validate and refine these models. Towards this goal, we describe an automated procedure for prioritizing ...