Now showing items 1-20 of 39

    • Active boundary annotation using random MAP perturbations 

      Maji, Subhransu; Hazan, Tamir; Jaakkola, Tommi S (PLMR, 2014-04)
      We address the problem of efficiently annotating labels of objects when they are structured. Often the distribution over labels can be described using a joint potential function over the labels for which sampling is provably ...
    • Approximate inference in additive factorial HMMs with application to energy disaggregation 

      Kolter, Jeremy Z.; Jaakkola, Tommi S. (Proceedings of Machine Learning Research, 2012-04)
      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 ...
    • Bidirectional Inference Networks:A Class of Deep Bayesian Networks for Health Profiling 

      Wang, Hao; He, Hao; Zhao, Mingmin; Jaakkola, Tommi S; Katabi, Dina (Association for the Advancement of Artificial Intelligence (AAAI), 2019-01)
      We consider the problem of inferring the values of an arbitrary set of variables (e.g., risk of diseases) given other observed variables (e.g., symptoms and diagnosed diseases) and high-dimensional signals (e.g., MRI images ...
    • Collaborative future event recommendation 

      Minkov, Einat; Charrow, Ben; Ledlie, Jonathan; Teller, Seth; Jaakkola, Tommi S. (Association for Computing Machinery, 2010-10)
      We demonstrate a method for collaborative ranking of future events. Previous work on recommender systems typically relies on feedback on a particular item, such as a movie, and generalizes this to other items or other ...
    • Controlling privacy in recommender systems 

      Xin, Yu; Jaakkola, Tommi S. (Neural Information Processing Systems, 2014)
      Recommender systems involve an inherent trade-off between accuracy of recommendations and the extent to which users are willing to release information about their preferences. In this paper, we explore a two-tiered notion ...
    • Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction 

      Coley, Connor Wilson; Barzilay, Regina; Green Jr, William H; Jaakkola, Tommi S; Jensen, Klavs F (American Chemical Society (ACS), 2017-07)
      The task of learning an expressive molecular representation is central to developing quantitative structure–activity and property relationships. Traditional approaches rely on group additivity rules, empirical measurements ...
    • Current and Future Roles of Artificial Intelligence in Medicinal Chemistry Synthesis 

      Struble, Thomas J; Jaakkola, Tommi S; Green Jr, William H; Barzilay, Regina (American Chemical Society (ACS), 2020-04)
      Artificial intelligence and machine learning have demonstrated their potential role in predictive chemistry and synthetic planning of small molecules; there are at least a few reports of companies employing in silico ...
    • Deriving neural architectures from sequence and graph kernels 

      Lei, Tao; Jin, Wengong; Barzilay, Regina; Jaakkola, Tommi S (MLResearch Press, 2017)
      The design of neural architectures for structured objects is typically guided by experimental insights rather than a formal process. In this work, we appeal to kernels over combinatorial structures, such as sequences and ...
    • Direct optimization through arg max for discrete variational auto-encoder 

      Gane, Andreea; Jaakkola, Tommi S (Morgan Kaufmann Publishers, 2019-12)
      Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates. In the discrete case, one can perform reparametrization using ...
    • Dual decomposition for parsing with non-projective head automata 

      Koo, Terry; Rush, Alexander Matthew; Collins, Michael; Jaakkola, Tommi S.; Sontag, David Alexander (Association for Computational Linguistics, 2010-10)
      This paper introduces algorithms for non-projective parsing based on dual decomposition. We focus on parsing algorithms for non-projective head automata, a generalization of head-automata models to non-projective structures. ...
    • From random walks to distances on unweighted graphs 

      Hashimoto, Tatsunori Benjamin; Jaakkola, Tommi S; Sun, Yi (Neural Information Processing Systems Foundation, Inc., 2015-12)
      Large unweighted directed graphs are commonly used to capture relations between entities. A fundamental problem in the analysis of such networks is to properly define the similarity or dissimilarity between any two vertices. ...
    • A game theoretic approach to class-wise selective rationalization 

      Chang, Shiyu; Zhang, Yang; Jaakkola, Tommi S
      © 2019 Neural information processing systems foundation. All rights reserved. Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. ...
    • Generative models for graph-based protein design 

      Ingraham, John; Garg, Vikas Kamur; Barzilay, Regina; Jaakkola, Tommi S
      Engineered proteins offer the potential to solve many problems in biomedicine, energy, and materials science, but creating designs that succeed is difficult in practice. A significant aspect of this challenge is the complex ...
    • Greed Is Good If Randomized: New Inference for Dependency Parsing 

      Zhang, Yuan; Lei, Tao; Barzilay, Regina; Jaakkola, Tommi S. (2014-10)
      Dependency parsing with high-order features results in a provably hard decoding problem. A lot of work has gone into developing powerful optimization methods for solving these combinatorial problems. In contrast, we explore, ...
    • High Dimensional Inference with Random Maximum A-Posteriori Perturbations 

      Maji, Subhransu; Jaakkola, Tommi S (Institute of Electrical and Electronics Engineers (IEEE), 2019-05)
      This paper presents a new approach, called perturb-max, for high-dimensional statistical inference in graphical models that is based on applying random perturbations followed by optimization. This framework injects randomness ...
    • Inverse Covariance Estimation for High-Dimensional Data in Linear Time and Space: Spectral Methods for Riccati and Sparse Models 

      Honorio, Jean; Jaakkola, Tommi S. (Association for Uncertainty in Artificial Intelligence (AUAI), 2013-07)
      We propose maximum likelihood estimation for learning Gaussian graphical models with a Gaussian (ℓ[2 over 2]) prior on the parameters. This is in contrast to the commonly used Laplace (ℓ[subscript 1) prior for encouraging ...
    • Learning bayesian network structure using lp relaxations 

      Jaakkola, Tommi S.; Sontag, David Alexander; Globerson, Amir; Meila, Marina (Society for Artificial Intelligence and Statistics, 2010-05)
      We propose to solve the combinatorial problem of finding the highest scoring Bayesian network structure from data. This structure learning problem can be viewed as an inference problem where the variables specify ...
    • Learning efficient random maximum a-posteriori predictors with non-decomposable loss functions 

      Hazan, Tamir; Maji, Subhransu; Keshet, Joseph; Jaakkola, Tommi S. (Neural Information Processing Systems, 2013)
      In this work we develop efficient methods for learning random MAP predictors for structured label problems. In particular, we construct posterior distributions over perturbations that can be adjusted via stochastic gradient ...
    • Learning efficiently with approximate inference via dual losses 

      Meshi, Ofer; Sontag, David Alexander; Jaakkola, Tommi S.; Globerson, Amir (International Machine Learning Society, 2010-01)
      Many structured prediction tasks involve complex models where inference is computationally intractable, but where it can be well approximated using a linear programming relaxation. Previous approaches for learning for ...
    • Lineage-based identification of cellular states and expression programs 

      Hashimoto, Tatsunori Benjamin; Jaakkola, Tommi S.; Sherwood, Richard; Mazzoni, Esteban O.; Wichterle, Hynek; e.a. (Oxford University Press, 2012-01)
      We present a method, LineageProgram, that uses the developmental lineage relationship of observed gene expression measurements to improve the learning of developmentally relevant cellular states and expression programs. ...