Now showing items 1-20 of 24

    • Analyzing Learned Molecular Representations for Property Prediction 

      Yang, Kevin; Swanson, Kyle; Jin, Wengong; Coley, Connor; Eiden, Philipp; e.a. (American Chemical Society (ACS), 2019)
      © 2019 American Chemical Society. Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: ...
    • Aspect-augmented Adversarial Networks for Domain Adaptation 

      Zhang, Yuan; Barzilay, Regina; Jaakkola, Tommi (MIT Press - Journals, 2017)
      <jats:p> We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain. Rather than training on target labels, we use a few keywords pertaining to ...
    • Convergence Rate Analysis of MAP Coordinate Minimization Algorithms 

      Meshi, Ofer; Jaakkola, Tommi; Globerson, Amir (2012)
      Finding maximum a posteriori (MAP) assignments in graphical models is an important task in many applications. Since the problem is generally hard, linear programming (LP) relaxations are often used. Solving these relaxations ...
    • DNA Binding and Games 

      Perez-Breva, Luis; Ortiz, Luis E.; Yeang, Chen-Hsiang, 1969-; Jaakkola, Tommi (2006-03-06)
      We propose a game-theoretic approach tolearn and predict coordinate binding of multiple DNA bindingregulators. The framework implements resource constrainedallocation of proteins to local neighborhoods as well as to ...
    • Generalized Low-Rank Approximations 

      Srebro, Nathan; Jaakkola, Tommi (2003-01-15)
      We study the frequent problem of approximating a target matrix with a matrix of lower rank. We provide a simple and efficient (EM) algorithm for solving {\\em weighted} low rank approximation problems, which, unlike simple ...
    • Generating molecules with optimized aqueous solubility using iterative graph translation 

      Bilodeau, Camille; Jin, Wengong; Xu, Hongyun; Emerson, Jillian A; Mukhopadhyay, Sukrit; e.a. (Royal Society of Chemistry (RSC), 2021-11)
      While molecular discovery is critical for solving many scientific problems, the time and resource costs of experiments make it intractable to fully explore chemical space. Here, we present a generative modeling framework ...
    • Grounding Language for Transfer in Deep Reinforcement Learning 

      Narasimhan, Karthik; Barzilay, Regina; Jaakkola, Tommi (AI Access Foundation, 2018)
      © 2018 AI Access Foundation. All rights reserved. In this paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL). Despite the wide-spread application of deep RL techniques, ...
    • Junction tree variational autoencoder for molecular graph generation 

      Jin, Wengong; Barzilay, Regina; Jaakkola, Tommi (2018)
      © 2018 by authors.All right reserved. We seek to automate the design of molecules based on specific chemical properties. In computational terms, this task involves continuous embedding and generation of molecular graphs. ...
    • Learning sleep stages from radio signals: A conditional adversarial architecture 

      Jaakkola, Tommi; Bianchi, Matt T.; Katabi, Dina; Yue, Shichao; Zhao, Mingmin (2017)
      © Copyright 2017 by the authors(s). We focus on predicting sleep stages from radio measurements without any attached sensors on subjects. We introduce a new predictive model that combines convolutional and recurrent neural ...
    • Learning Tree Structured Potential Games 

      Garg, Vikas K.; Jaakkola, Tommi (2016)
      © 2016 NIPS Foundation - All Rights Reserved. Many real phenomena, including behaviors, involve strategic interactions that can be learned from data. We focus on learning tree structured potential games where equilibria ...
    • Local aggregative games 

      Jaakkola, Tommi; Garg, Vikas (2017)
      © 2017 Neural information processing systems foundation. All rights reserved. Aggregative games provide a rich abstraction to model strategic multi-agent interactions. We introduce local aggregative games, where the payoff ...
    • Managing the 802.11 Energy/Performance Tradeoff with Machine Learning 

      Monteleoni, Claire; Balakrishnan, Hari; Feamster, Nick; Jaakkola, Tommi (2004-10-27)
      This paper addresses the problem of managing the tradeoff betweenenergy consumption and performance in wireless devices implementingthe IEEE 802.11 standard. To save energy, the 802.11 specificationproposes a power-saving ...
    • Maximum Entropy Discrimination 

      Jaakkola, Tommi; Meila, Marina; Jebara, Tony (1999-12-01)
      We present a general framework for discriminative estimation based on the maximum entropy principle and its extensions. All calculations involve distributions over structures and/or parameters rather than specific ...
    • Mean Field Theory for Sigmoid Belief Networks 

      Saul, Lawrence K.; Jaakkola, Tommi; Jordan, Michael I. (1996-08-01)
      We develop a mean field theory for sigmoid belief networks based on ideas from statistical mechanics. Our mean field theory provides a tractable approximation to the true probability distribution in these networks; it ...
    • Modeling Persistent Trends in Distributions 

      Mueller, Jonas; Jaakkola, Tommi; Gifford, David (Informa UK Limited, 2018)
      © 2018, © 2018 American Statistical Association. We present a nonparametric framework to model a short sequence of probability distributions that vary both due to underlying effects of sequential progression and confounding ...
    • On the Convergence of Stochastic Iterative Dynamic Programming Algorithms 

      Jaakkola, Tommi; Jordan, Michael I.; Singh, Satinder P. (1993-08-01)
      Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD(lambda) algorithm of Sutton ...
    • On the Partition Function and Random Maximum A-Posteriori Perturbations 

      Hazan, Tamir; Jaakkola, Tommi (2012)
      In this paper we relate the partition function to the max-statistics of random variables. In particular, we provide a novel framework for approximating and bounding the partition function using MAP inference on randomly ...
    • Online Learning of Non-stationary Sequences 

      Monteleoni, Claire; Jaakkola, Tommi (2005-11-17)
      We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. We derive upper and lower relative loss bounds for a class of universal learning algorithms involving ...
    • Sequence to better sequence: Continuous revision of combinatorial structures 

      Jaakkola, Tommi; Gifford, David; Mueller, Jonas (2017)
      © 2017 by the author(s). We present a model that, after learning on observations of (sequence, outcome) pairs, can be efficiently used to revise a new sequence in order to improve its associated outcome. Our framework ...
    • Stable Mixing of Complete and Incomplete Information 

      Corduneanu, Adrian; Jaakkola, Tommi (2001-11-08)
      An increasing number of parameter estimation tasks involve the use of at least two information sources, one complete but limited, the other abundant but incomplete. Standard algorithms such as EM (or em) used in this context ...