In this work, we present a MCTS-based Go-playing program which uses convolutional networks in all parts. Our method performs MCTS in batches, explores the Monte Carlo search tree using Thompson sampling and a convolutional network, and evaluates convnet-based rollouts on the GPU. We achieve strong win rates against open source Go programs and attain competitive results against state of the art convolutional net-based Go-playing programs.
We model online recommendation systems using the hidden Markov multi-state restless multi-armed bandit problem. To solve this we present Monte Carlo rollout policy. We illustrate numerically that Monte Carlo rollout policy performs better than myopic policy for arbitrary transition dynamics with no specific structure. But, when some structure is imposed on the transition dynamics, myopic policy performs better than Monte Carlo rollout policy.
Restless multi-armed bandits with partially observable states has applications in communication systems, age of information and recommendation systems. In this paper, we study multi-state partially observable restless bandit models. We consider three different models based on information observable to decision maker -- 1) no information is observable from actions of a bandit 2) perfect information from bandit is observable only for one action on bandit, there is a fixed restart state, i.e., transition occurs from all other states to that state 3) perfect state information is available to decis…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Microsoft Research（微软研究院）；Columbia University（哥伦比亚大学）
Sequence generation models are commonly refined with reinforcement learning over user-defined metrics. However, high gradient variance hinders the practical use of this method. To stabilize this method, we adapt to contextual generation of categorical sequences a policy gradient estimator, which evaluates a set of correlated Monte Carlo (MC) rollouts for variance control. Due to the correlation, the number of unique rollouts is random and adaptive to model uncertainty; those rollouts naturally become baselines for each other, and hence are combined to effectively reduce gradient variance. We a…
Facebook AI Research（脸书人工智能研究院）；Rutgers University（罗格斯大学）
Competing with top human players in the ancient game of Go has been a long-term goal of artificial intelligence. Go's high branching factor makes traditional search techniques ineffective, even on leading-edge hardware, and Go's evaluation function could change drastically with one stone change. Recent works [Maddison et al. (2015); Clark & Storkey (2015)] show that search is not strictly necessary for machine Go players. A pure pattern-matching approach, based on a Deep Convolutional Neural Network (DCNN) that predicts the next move, can perform as well as Monte Carlo Tree Search (MCTS)-based…
Seattle AI Lab, Kwai Inc.（快手公司西雅图人工智能实验室）；Tencent AI Lab（腾讯人工智能实验室）
Monte Carlo Tree Search (MCTS) algorithms have achieved great success on many challenging benchmarks (e.g., Computer Go). However, they generally require a large number of rollouts, making their applications costly. Furthermore, it is also extremely challenging to parallelize MCTS due to its inherent sequential nature: each rollout heavily relies on the statistics (e.g., node visitation counts) estimated from previous simulations to achieve an effective exploration-exploitation tradeoff. In spite of these difficulties, we develop an algorithm, WU-UCT, to effectively parallelize MCTS, which ach…
University of California, Los Angeles（加州大学洛杉矶分校）；Kwai Inc.（快手公司）；Tencent AI Lab（腾讯人工智能实验室）
Despite its groundbreaking success in Go and computer games, Monte Carlo Tree Search (MCTS) is computationally expensive as it requires a substantial number of rollouts to construct the search tree, which calls for effective parallelization. However, how to design effective parallel MCTS algorithms has not been systematically studied and remains poorly understood. In this paper, we seek to lay its first theoretical foundation, by examining the potential performance loss caused by parallelization when achieving a desired speedup. In particular, we discover the necessary conditions of achieving …
University of Science and Technology of China（中国科学技术大学）；North Carolina University（北卡罗来纳大学）；National University of Singapore（新加坡国立大学）
Today, there are two major understandings for graph convolutional networks, i.e., in the spectral and spatial domain. But both lack transparency. In this work, we introduce a new understanding for it -- data augmentation, which is more transparent than the previous understandings. Inspired by it, we propose a new graph learning paradigm -- Monte Carlo Graph Learning (MCGL). The core idea of MCGL contains: (1) Data augmentation: propagate the labels of the training set through the graph structure and expand the training set; (2) Model training: use the expanded training set to train traditional…
The precise simulation of particle transport through detectors remains a key element for the successful interpretation of high energy physics results. However, Monte Carlo based simulation is extremely demanding in terms of computing resources. This challenge motivates investigations of faster, alternative approaches for replacing the standard Monte Carlo approach. We apply Generative Adversarial Networks (GANs), a deep learning technique, to replace the calorimeter detector simulations and speeding up the simulation time by orders of magnitude. We follow a previous approach which used three-d…
College of Aerospace Science and Engineering, National University of Defense Technology（国防科技大学航空航天学院）；Defense Innovation Institute, Chinese Academy of Military Science（中国人民解放军军事科学院国防创新研究院）
Temperature field reconstruction is essential for analyzing satellite heat reliability. As a representative machine learning model, the deep convolutional neural network (DCNN) is a powerful tool for reconstructing the satellite temperature field. However, DCNN needs a lot of labeled data to learn its parameters, which is contrary to the fact that actual satellite engineering can only acquire noisy unlabeled data. To solve the above problem, this paper proposes an unsupervised method, i.e., the physics-informed deep Monte Carlo quantile regression method, for reconstructing temperature field a…
Recently, adaptive graph convolutional network based traffic prediction methods, learning a latent graph structure from traffic data via various attention-based mechanisms, have achieved impressive performance. However, they are still limited to find a better description of spatial relationships between traffic conditions due to: (1) ignoring the prior of the observed topology of the road network; (2) neglecting the presence of negative spatial relationships; and (3) lacking investigation on uncertainty of the graph structure. In this paper, we propose a Bayesian Graph Convolutional Network (B…
Monte Carlo Tree Diffusion with Multiple Experts for Protein Design
University of Chicago（芝加哥大学）；Data Science Institute（数据科学研究所）；Department of Biochemistry and Molecular Biology（生物化学与分子生物学系）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；Argonne National Laboratory（阿贡国家实验室）；Princeton University（普林斯顿大学）
Scaling Kinetic Monte-Carlo Simulations of Grain Growth with Combined Convolutional and Graph Neural Networks
Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA（电气与计算机工程系，佛罗里达大学，盖恩斯维尔，佛罗里达州，美国）；Northwestern University（西北大学）；Lawrence Livermore National Laboratory, Livermore, CA, United States（劳伦斯利弗莫尔国家实验室，利弗莫尔，加利福尼亚州，美国）
University of Notre Dame（圣母大学）；Sandia National Laboratories（桑迪亚国家实验室）；Stanford University（斯坦福大学）
We analyze the regression accuracy of convolutional neural networks assembled from encoders, decoders and skip connections and trained with multifidelity data. Besides requiring significantly less trainable parameters than equivalent fully connected networks, encoder, decoder, encoder-decoder or decoder-encoder architectures can learn the mapping between inputs to outputs of arbitrary dimensionality. We demonstrate their accuracy when trained on a few high-fidelity and many low-fidelity data generated from models ranging from one-dimensional functions to Poisson equation solvers in two-dimensi…
A Monte Carlo k-nearest neighbours (KNN) and a multi-resolution convolutional neural network (CNN) were developed to detect the presences of multiple gasses in near infrared (IR) spectrums. High Resolution Transmission database was used to synthesize the near IR spectrums. Monte Carlo KNN determined the optimal kernel sizes and the optimal number of channels. The multi-resolution CNN, composed of multiple different kernels, was created using the optimal kernel sizes and the optimal number of channels. The multi-resolution CNN outperforms the multilayer perceptron and the partial least squares.
Monte Carlo tree search (MCTS) is extremely popular in computer Go which determines each action by enormous simulations in a broad and deep search tree. However, human experts select most actions by pattern analysis and careful evaluation rather than brute search of millions of future nteractions. In this paper, we propose a computer Go system that follows experts way of thinking and playing. Our system consists of two parts. The first part is a novel deep alternative neural network (DANN) used to generate candidates of next move. Compared with existing deep convolutional neural network (DCNN)…
College of Aerospace Science and Engineering National University of Defense Technology（国防科技大学航空航天学院）；Defense Innovation Institute Chinese Academy of Military Science（中国人民解放军军事科学院国防创新研究院）
For the temperature field reconstruction (TFR), a complex image-to-image regression problem, the convolutional neural network (CNN) is a powerful surrogate model due to the convolutional layer's good image feature extraction ability. However, a lot of labeled data is needed to train CNN, and the common CNN can not quantify the aleatoric uncertainty caused by data noise. In actual engineering, the noiseless and labeled training data is hardly obtained for the TFR. To solve these two problems, this paper proposes a deep Monte Carlo quantile regression (Deep MC-QR) method for reconstructing the t…
University of Toronto（多伦多大学）；Google DeepMind（谷歌DeepMind）；Google Brain（谷歌大脑）
The game of Go is more challenging than other board games, due to the difficulty of constructing a position or move evaluation function. In this paper we investigate whether deep convolutional networks can be used to directly represent and learn this knowledge. We train a large 12-layer convolutional neural network by supervised learning from a database of human professional games. The network correctly predicts the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. When the trained convolutional network was used directly to play games of Go, without any search, i…
As the deep neural networks are being applied to complex tasks, the size of the networks and architecture increases and their topology becomes more complicated too. At the same time, training becomes slow and at some instances inefficient. This motivated the introduction of various normalization techniques such as Batch Normalization and Layer Normalization. The aforementioned normalization methods use arithmetic operations to compute an approximation statistics (mainly the first and second moments) of the layer's data and use it to normalize it. The aforementioned methods use plain Monte Carl…
Brown University（布朗大学）；Worcester Polytechnic Institute（伍斯特理工学院）；Facebook AI Research（脸书人工智能研究院）
Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time. In this paper, we present a novel scalable Monte Carlo Tree Search (MCTS) based NAS agent, named AlphaX, to tackle these two aspects. AlphaX improves the search efficiency by adaptively balancing the exploration and exploitation at the state level, and by a Meta-Deep Neural Network (DNN)…
The graph convolutional networks (GCN) recently proposed by Kipf and Welling are an effective graph model for semi-supervised learning. This model, however, was originally designed to be learned with the presence of both training and test data. Moreover, the recursive neighborhood expansion across layers poses time and memory challenges for training with large, dense graphs. To relax the requirement of simultaneous availability of test data, we interpret graph convolutions as integral transforms of embedding functions under probability measures. Such an interpretation allows for the use of Mon…
UNSW Sydney（悉尼新南威尔士大学）；Manipal Institute of Technology（马尼帕尔理工学院）
Deep learning models, such as convolutional neural networks, have long been applied to image and multi-media tasks, particularly those with structured data. More recently, there has been more attention to unstructured data that can be represented via graphs. These types of data are often found in health and medicine, social networks, and research data repositories. Graph convolutional neural networks have recently gained attention in the field of deep learning that takes advantage of graph-based data representation with automatic feature extraction via convolutions. Given the popularity of the…
Mastering the game of Go has remained a long standing challenge to the field of AI. Modern computer Go systems rely on processing millions of possible future positions to play well, but intuitively a stronger and more 'humanlike' way to play the game would be to rely on pattern recognition abilities rather then brute force computation. Following this sentiment, we train deep convolutional neural networks to play Go by training them to predict the moves made by expert Go players. To solve this problem we introduce a number of novel techniques, including a method of tying weights in the network …
The quantification of uncertainty on fluid flow in porous media is often hampered by multi-scale heterogeneity and insufficient site characterization. Monte-Carlo simulation (MCS), which runs numerical simulations for a large number of realization of input parameters , becomes infeasible when simulation cost is expensive or the degree of uncertainty is large. Many deep-neural-network-based methods are developed in order to replace the numerical flow simulation, but previous studies focused only on generating several snapshots of outputs at the fixed time steps, and lack to reflect the time dep…
Skobeltsyn Institute of Nuclear Physics, M.V. Lomonosov Moscow State University（莫斯科国立罗蒙诺索夫大学斯科别利岑核物理研究所）
Extensive air showers created by high-energy particles interacting with the Earth atmosphere can be detected using imaging atmospheric Cherenkov telescopes (IACTs). The IACT images can be analyzed to distinguish between the events caused by gamma rays and by hadrons and to infer the parameters of the event such as the energy of the primary particle. We use convolutional neural networks (CNNs) to analyze Monte Carlo-simulated images from the telescopes of the TAIGA experiment. The analysis includes selection of the images corresponding to the showers caused by gamma rays and estimating the ener…
Being able to reach any desired location in the environment can be a valuable asset for an agent. Learning a policy to navigate between all pairs of states individually is often not feasible. An all-goals updating algorithm uses each transition to learn Q-values towards all goals simultaneously and off-policy. However the expensive numerous updates in parallel limited the approach to small tabular cases so far. To tackle this problem we propose to use convolutional network architectures to generate Q-values and updates for a large number of goals at once. We demonstrate the accuracy and genera…
Université de Lorraine（洛林大学）；CentraleSupélec（巴黎中央理工-高等电力学院）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；Université de Paris（巴黎大学）；Astroparticule et Cosmologie（天体粒子与宇宙学实验室）
Cosmic shear estimation is an essential scientific goal for large galaxy surveys. It refers to the coherent distortion of distant galaxy images due to weak gravitational lensing along the line of sight. It can be used as a tracer of the matter distribution in the Universe. The unbiased estimation of the local value of the cosmic shear can be obtained via Bayesian analysis which relies on robust estimation of the galaxies ellipticity (shape) posterior distribution. This is not a simple problem as, among other things, the images may be corrupted with strong background noise. For current and comi…
As an important Markov Chain Monte Carlo (MCMC) method, stochastic gradient Langevin dynamics (SGLD) algorithm has achieved great success in Bayesian learning and posterior sampling. However, SGLD typically suffers from slow convergence rate due to its large variance caused by the stochastic gradient. In order to alleviate these drawbacks, we leverage the recently developed Laplacian Smoothing (LS) technique and propose a Laplacian smoothing stochastic gradient Langevin dynamics (LS-SGLD) algorithm. We prove that for sampling from both log-concave and non-log-concave densities, LS-SGLD achieve…
Microsoft Research（微软研究院）；University of California, Los Angeles（加州大学洛杉矶分校）
The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of what they have learned and how to further improve them. This paper investigates generative modeling of CNNs. The main contributions include: (1) We construct a generative model for the CNN in the form of exponential tilting of a reference distribution. (2) We propose a generative gradient for pre-training CNNs by a non-parametric importance sampling scheme, whi…
Research Institute of Applied Physics, Irkutsk State University（伊尔库茨克国立大学应用物理研究所）；Skobeltsyn Institute of Nuclear Physics, M.V. Lomonosov Moscow State University（莫斯科国立罗蒙诺索夫大学斯科别利岑核物理研究所）
The imaging Cherenkov telescopes TAIGA-IACT, located in the Tunka valley of the republic Buryatia, accumulate a lot of data in a short period of time which must be efficiently and quickly analyzed. One of the methods of such analysis is the machine learning, which has proven its effectiveness in many technological and scientific fields in recent years. The aim of the work is to study the possibility of the machine learning application to solve the tasks set for TAIGA-IACT: the identification of the primary particle of cosmic rays and reconstruction their physical parameters. In the work the me…
Machine learning a fixed point action for SU(3) gauge theory with a gauge equivariant convolutional neural network
University of the Pacific（太平洋大学）；Institute for Theoretical Physics, TU Wien（维也纳技术大学理论物理研究所）；Institute for Theoretical Physics, University of Bern（伯尔尼大学理论物理研究所）
Yuanpei College, Peking University（北京大学元培学院）；Key Laboratory of Machine Perception, Ministry of Education, Peking University（北京大学教育部机器感知重点实验室）
Graph Convolutional Networks (GCNs) have proved to be a most powerful architecture in aggregating local neighborhood information for individual graph nodes. Low-rank proximities and node features are successfully leveraged in existing GCNs, however, attributes that graph links may carry are commonly ignored, as almost all of these models simplify graph links into binary or scalar values describing node connectedness. In our paper instead, links are reverted to hypostatic relationships between entities with descriptional attributes. We propose GCN-LASE (GCN with Link Attributes and Sampling Est…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Beckman Institute（贝克曼研究所）
In this paper, we develop a convolutional neural network model to predict the mechanical properties of a two-dimensional checkerboard composite quantitatively. The checkerboard composite possesses two phases, one phase is soft and ductile while the other is stiff and brittle. The ground-truth data used in the training process are obtained from finite element analyses under the assumption of plane stress. Monte Carlo simulations and central limit theorem are used to find the size of the dataset needed. Once the training process is completed, the developed model is validated using data unseen du…
In the modern age of social media and networks, graph representations of real-world phenomena have become an incredibly useful source to mine insights. Often, we are interested in understanding how entities in a graph are interconnected. The Graph Neural Network (GNN) has proven to be a very useful tool in a variety of graph learning tasks including node classification, link prediction, and edge classification. However, in most of these tasks, the graph data we are working with may be noisy and may contain spurious edges. That is, there is a lot of uncertainty associated with the underlying gr…
We are interested in the development of surrogate models for uncertainty quantification and propagation in problems governed by stochastic PDEs using a deep convolutional encoder-decoder network in a similar fashion to approaches considered in deep learning for image-to-image regression tasks. Since normal neural networks are data intensive and cannot provide predictive uncertainty, we propose a Bayesian approach to convolutional neural nets. A recently introduced variational gradient descent algorithm based on Stein's method is scaled to deep convolutional networks to perform approximate Baye…
Durham University（杜伦大学）；Institute for Particle Physics Phenomenology（粒子物理现象学研究所）
Chiral magnets have attracted a large amount of research interest in recent years because they support a variety of topological defects, such as skyrmions and bimerons, and allow for their observation and manipulation through several techniques. They also have a wide range of applications in the field of spintronics, particularly in developing new technologies for memory storage devices. However, the vast amount of data generated in these experimental and theoretical studies requires adequate tools, among which machine learning is crucial. We use a Convolutional Neural Network (CNN) to identif…
Northwestern University（西北大学）；Northwestern Memorial Hospital（西北纪念医院）
We propose a mesh-based technique to aid in the classification of Alzheimer's disease dementia (ADD) using mesh representations of the cortex and subcortical structures. Deep learning methods for classification tasks that utilize structural neuroimaging often require extensive learning parameters to optimize. Frequently, these approaches for automated medical diagnosis also lack visual interpretability for areas in the brain involved in making a diagnosis. This work: (a) analyzes brain shape using surface information of the cortex and subcortical structures, (b) proposes a residual learning fr…
