Now showing items 1-20 of 42

    • Accelerating Markov chain Monte Carlo via parallel predictive prefetching 

      Angelino, Elaine Lee (2014-10-21)
      We present a general framework for accelerating a large class of widely used Markov chain Monte Carlo (MCMC) algorithms. This dissertation demonstrates that MCMC inference can be accelerated in a model of parallel computation ...
    • Accelerating MCMC with Parallel Predictive Prefetching 

      Angelino, Elaine; Kohler, Eddie W; Waterland, Amos; Seltzer, Margo I.; Adams, Ryan Prescott (AUAI Press, 2014)
      Parallel predictive prefetching is a new frame- work for accelerating a large class of widely- used Markov chain Monte Carlo (MCMC) algorithms. It speculatively evaluates many potential steps of an MCMC chain in parallel ...
    • ASC: Automatically Scalable Computation 

      Waterland, Amos; Angelino, Elaine; Adams, Ryan Prescott; Appavoo, Jonathan; Seltzer, Margo I. (Association of Computing Machinery, 2014)
      We present an architecture designed to transparently and automatically scale the performance of sequential programs as a function of the hardware resources available. The architecture is predicated on a model of computation ...
    • Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules 

      Gómez-Bombarelli, Rafael; Wei, Jennifer Nansean; Duvenaud, David; Hernández-Lobato, José Miguel; Sánchez-Lengeling, Benjamín; Sheberla, Dennis; Aguilera-Iparraguirre, Jorge; Hirzel, Timothy D.; Adams, Ryan Prescott; Aspuru-Guzik, Alan (American Chemical Society (ACS), 2018)
      We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through ...
    • Avoiding pathologies in very deep networks 

      Duvenaud, David; Rippel, Oren; Adams, Ryan Prescott; Ghahramani, Zoubin (Journal of Machine Learning Research, 2014)
      Choosing appropriate architectures and regularization strategies of deep networks is crucial to good predictive performance. To shed light on this problem, we analyze the analogous problem of constructing useful priors on ...
    • Bayesian Methods for Discovering Structure in Neural Spike Trains 

      Linderman, Scott Warren (2016-05-18)
      Neuroscience is entering an exciting new age. Modern recording technologies enable simultaneous measurements of thousands of neurons in organisms performing complex behaviors. Such recordings offer an unprecedented opportunity ...
    • Bayesian Painting by Numbers: Flexible Priors for Colour-Invariant Object Recognition 

      Chua, Jeroen C.; Givoni, Inmar E.; Adams, Ryan Prescott; Frey, Brendan J. (Springer-Verlag, 2013)
      Generative models of images should take into account transformations of geometry and reflectance. Then, they can provide explanations of images that are factorized into intrinsic properties that are useful for subsequent ...
    • Bootstrap Learning Via Modular Concept Discovery 

      Dechter, Eyal; Malmaud, Jonathan; Adams, Ryan Prescott; Tenenbaum, Joshua B. (AAAI Press/International Joint Conferences on Artificial Intelligence, 2013)
      Suppose a learner is faced with a domain of problems about which it knows nearly nothing. It does not know the distribution of problems, the space of solutions is not smooth, and the reward signal is uninformative, providing ...
    • Cardinality Restricted Boltzmann Machines 

      Swersky, Kevin; Tarlow, Daniel; Sutskever, Ilya; Salakhutdinov, Ruslan; Zemel, Richard; Adams, Ryan Prescott (Massachusetts Institute of Technology Press, 2012)
      The Restricted Boltzmann Machine (RBM) is a popular density model that is also good for extracting features. A main source of tractability in RBM models is that, given an input, the posterior distribution over hidden ...
    • Computational Caches 

      Waterland, Amos; Angelino, Elaine Lee; Cubuk, Ekin Dogus; Kaxiras, Efthimios; Adams, Ryan Prescott; Appavoo, Jonathan; Seltzer, Margo I. (ACM Press, 2013)
      Caching is a well-known technique for speeding up computation. We cache data from file systems and databases; we cache dynamically generated code blocks; we cache page translations in TLBs. We propose to cache the act of ...
    • Contrastive Learning Using Spectral Methods 

      Zou, James Yang; Hsu, Daniel; Parkes, David C.; Adams, Ryan Prescott (Neural Information Processing Systems Foundation, 2013)
      In many natural settings, the analysis goal is not to characterize a single data set in isolation, but rather to understand the difference between one set of observations and another. For example, given a background corpus ...
    • Convolutional Networks on Graphs for Learning Molecular Fingerprints. 

      Aspuru-Guzik, Alan; Duvenaud, David; Maclaurin, Dougal; Aguilera-Iparraguire, Jorge; Gomez-Bombarelli, Rafael; Hirzel, Timothy D.; Adams, Ryan Prescott (Neural Information Processing Systems Foundation, Inc., 2015)
      We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present ...
    • A Determinantal Point Process Latent Variable Model for Inhibition in Neural Spiking Data 

      Snoek, Jasper; Zemel, Richard; Adams, Ryan Prescott (Curran Associates, Inc., 2013)
      Point processes are popular models of neural spiking behavior as they provide a statistical distribution over temporal sequences of spikes and help to reveal the complexities underlying a series of recorded action potentials. ...
    • Diagnosis of iron deficiency anemia using density-based fractionation of red blood cells 

      Hennek, Jonathan; Kumar, Ashok Ashwin; Wiltschko, Alexander Bame; Patton, Matthew Reiser; Lee, Si Yi Ryan; Brugnara, Carlo; Adams, Ryan Prescott; Whitesides, George McClelland (Royal Society of Chemistry (RSC), 2016)
      Iron deficiency anemia (IDA) is a nutritional disorder that impacts over one billion people worldwide, it causes permanent cognitive impairment in children, fatigue in adults, and suboptimal outcomes in pregnancy. IDA can ...
    • Discovering Latent Network Structure in Point Process Data 

      Linderman, Scott; Adams, Ryan Prescott (Journal of Machine Learning Research, 2014)
      Networks play a central role in modern data analysis, enabling us to reason about systems by studying the relationships between their parts. Most often in network analysis, the edges are given. However, in many systems it ...
    • Discovering Shared Cardiovascular Dynamics within a Patient Cohort 

      Nemati, Shamim; Lehman, Li-wei H.; Adams, Ryan Prescott; Malhotra, Atul (Institute of Electrical and Electronics Engineers, 2012)
      Cardiovascular variables such as heart rate (HR) and blood pressure (BP) are robustly regulated by an underlying control system. Time series of HR and BP exhibit distinct dynamical patterns of interaction in response to ...
    • Discovering Shared Dynamics in Physiological Signals: Application to Patient Monitoring in ICU 

      Lehman, Li-wei H.; Nemati, Shamim; Adams, Ryan Prescott; Mark, Roger Greenwood (Institute of Electrical and Electronics Engineers, 2012)
      Modern clinical databases include time series of vital signs, which are often recorded continuously during a hospital stay. Over several days, these recordings may yield many thousands of samples. In this work, we explore ...
    • Factorized Point Process Intensities: A Spatial Analysis of Professional Basketball 

      Miller, Andrew; Bornn, Luke; Adams, Ryan Prescott; Goldsberry, Kirk P (Journal of Machine Learning Research, 2014)
      We develop a machine learning approach to represent and analyze the underlying spatial structure that governs shot selection among professional basketball players in the NBA. Typically, NBA players are discussed and compared ...
    • Fast Exact Inference for Recursive Cardinality Models 

      Tarlow, Daniel; Swersky, Kevin; Zemel, Richard S.; Adams, Ryan Prescott (AUAI Press, 2012)
      Cardinality potentials are a generally useful class of high order potential that affect probabilities based on how many of D binary variables are active. Maximum a posteriori (MAP) inference for cardinality potential models ...
    • Firefly Monte Carlo: Exact MCMC with Subsets of Data 

      Maclaurin, Dougal; Adams, Ryan Prescott (AUAI Press, 2014)
      Markov chain Monte Carlo (MCMC) is a popular and successful general-purpose tool for Bayesian inference. However, MCMC cannot be practically applied to large data sets because of the prohibitive cost of evaluating every ...