arXiv subjects

Prasanna Balaprakash

Publications and source records attributed to Prasanna Balaprakash.

At least 91 records · Page 5Linked to original sources

arXiv2021

Customized Monte Carlo Tree Search for LLVM/Polly's Composable Loop Optimization Transformations

Polly is the LLVM project's polyhedral loop nest optimizer. Recently, user-directed loop transformation pragmas were proposed based on LLVM/Clang and Polly. The search space exposed by the transformation pragmas is a tree, wherein each node represents a specific combination of loop transformations that can be applied to the code resulting from the parent node's loop transformations. We have developed a search algorithm based on Monte Carlo tree search (MCTS) to find the best combination of loop transformations. Our algorithm consists of two phases: exploring loop transformations at different depths of the tree to identify promising regions in the tree search space and exploiting those regions by performing a local search. Moreover, a restart mechanism is used to avoid the MCTS getting trapped in a local solution. The best and worst solutions are transferred from the previous phases of the restarts to leverage the search history. We compare our approach with random, greedy, and breadth-first search methods on PolyBench kernels and ECP proxy applications. Experimental results show that our MCTS algorithm finds pragma combinations with a speedup of 2.3x over Polly's heuristic optimizations on average.

cs.PL↗

arXiv2021

Autotuning PolyBench Benchmarks with LLVM Clang/Polly Loop Optimization Pragmas Using Bayesian Optimization (extended version)

In this paper, we develop a ytopt autotuning framework that leverages Bayesian optimization to explore the parameter space search and compare four different supervised learning methods within Bayesian optimization and evaluate their effectiveness. We select six of the most complex PolyBench benchmarks and apply the newly developed LLVM Clang/Polly loop optimization pragmas to the benchmarks to optimize them. We then use the autotuning framework to optimize the pragma parameters to improve their performance. The experimental results show that our autotuning approach outperforms the other compiling methods to provide the smallest execution time for the benchmarks syr2k, 3mm, heat-3d, lu, and covariance with two large datasets in 200 code evaluations for effectively searching the parameter spaces with up to 170,368 different configurations. We find that the Floyd-Warshall benchmark did not benefit from autotuning because Polly uses heuristics to optimize the benchmark to make it run much slower. To cope with this issue, we provide some compiler option solutions to improve the performance. Then we present loop autotuning without a user's knowledge using a simple mctree autotuning framework to further improve the performance of the Floyd-Warshall benchmark. We also extend the ytopt autotuning framework to tune a deep learning application.

cs.LG↗

arXiv2021

Neuromodulated Neural Architectures with Local Error Signals for Memory-Constrained Online Continual Learning

The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual learning rely on stochastic gradient descent and its variants. However, these algorithms have to implement various strategies, such as memory buffers or replay, to overcome well-known shortcomings of stochastic gradient descent methods in terms of stability, greed, and short-term memory. To that end, we develop a biologically-inspired light weight neural network architecture that incorporates local learning and neuromodulation to enable input processing over data streams and online learning. Next, we address the challenge of hyperparameter selection for tasks that are not known in advance by implementing transfer metalearning: using a Bayesian optimization to explore a design space spanning multiple local learning rules and their hyperparameters, we identify high performing configurations in classical single task online learning and we transfer them to continual learning tasks with task-similarity considerations. We demonstrate the efficacy of our approach on both single task and continual learning setting. For the single task learning setting, we demonstrate superior performance over other local learning approaches on the MNIST, Fashion MNIST, and CIFAR-10 datasets. Using high performing configurations metalearned in the single task learning setting, we achieve superior continual learning performance on Split-MNIST, and Split-CIFAR-10 data as compared with other memory-constrained learning approaches, and match that of the state-of-the-art memory-intensive replay-based approaches.

cs.LG↗

arXiv2021

Data-Driven Random Access Optimization in Multi-Cell IoT Networks with NOMA

Non-orthogonal multiple access (NOMA) is a key technology to enable massive machine type communications (mMTC) in 5G networks and beyond. In this paper, NOMA is applied to improve the random access efficiency in high-density spatially-distributed multi-cell wireless IoT networks, where IoT devices contend for accessing the shared wireless channel using an adaptive p-persistent slotted Aloha protocol. To enable a capacity-optimal network, a novel formulation of random channel access management is proposed, in which the transmission probability of each IoT device is tuned to maximize the geometric mean of users' expected capacity. It is shown that the network optimization objective is high dimensional and mathematically intractable, yet it admits favourable mathematical properties that enable the design of efficient data-driven algorithmic solutions which do not require a priori knowledge of the channel model or network topology. A centralized model-based algorithm and a scalable distributed model-free algorithm, are proposed to optimally tune the transmission probabilities of IoT devices and attain the maximum capacity. The convergence of the proposed algorithms to the optimal solution is further established based on convex optimization and game-theoretic analysis. Extensive simulations demonstrate the merits of the novel formulation and the efficacy of the proposed algorithms.

cs.NI↗

arXiv2021

Learning Symbolic Expressions: Mixed-Integer Formulations, Cuts, and Heuristics

In this paper we consider the problem of learning a regression function without assuming its functional form. This problem is referred to as symbolic regression. An expression tree is typically used to represent a solution function, which is determined by assigning operators and operands to the nodes. The symbolic regression problem can be formulated as a nonconvex mixed-integer nonlinear program (MINLP), where binary variables are used to assign operators and nonlinear expressions are used to propagate data values through nonlinear operators such as square, square root, and exponential. We extend this formulation by adding new cuts that improve the solution of this challenging MINLP. We also propose a heuristic that iteratively builds an expression tree by solving a restricted MINLP. We perform computational experiments and compare our approach with a mixed-integer program-based method and a neural-network-based method from the literature.

math.OC↗

arXiv2020

Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders

A common strategy for the dimensionality reduction of nonlinear partial differential equations relies on the use of the proper orthogonal decomposition (POD) to identify a reduced subspace and the Galerkin projection for evolving dynamics in this reduced space. However, advection-dominated PDEs are represented poorly by this methodology since the process of truncation discards important interactions between higher-order modes during time evolution. In this study, we demonstrate that an encoding using convolutional autoencoders (CAEs) followed by a reduced-space time evolution by recurrent neural networks overcomes this limitation effectively. We demonstrate that a truncated system of only two latent-space dimensions can reproduce a sharp advecting shock profile for the viscous Burgers equation with very low viscosities, and a six-dimensional latent space can recreate the evolution of the inviscid shallow water equations. Additionally, the proposed framework is extended to a parametric reduced-order model by directly embedding parametric information into the latent space to detect trends in system evolution. Our results show that these advection-dominated systems are more amenable to low-dimensional encoding and time evolution by a CAE and recurrent neural network combination than the POD Galerkin technique.

physics.flu-dyn↗

arXiv2020

Machine learning-based inversion of nuclear responses

A microscopic description of the interaction of atomic nuclei with external electroweak probes is required for elucidating aspects of short-range nuclear dynamics and for the correct interpretation of neutrino oscillation experiments. Nuclear quantum Monte Carlo methods infer the nuclear electroweak response functions from their Laplace transforms. Inverting the Laplace transform is a notoriously ill-posed problem; and Bayesian techniques, such as maximum entropy, are typically used to reconstruct the original response functions in the quasielastic region. In this work, we present a physics-informed artificial neural network architecture suitable for approximating the inverse of the Laplace transform. Utilizing simulated, albeit realistic, electromagnetic response functions, we show that this physics-informed artificial neural network outperforms maximum entropy in both the low-energy transfer and the quasielastic regions, thereby allowing for robust calculations of electron scattering and neutrino scattering on nuclei and inclusive muon capture rates.

nucl-th↗

arXiv2020

Autotuning PolyBench Benchmarks with LLVM Clang/Polly Loop Optimization Pragmas Using Bayesian Optimization

An autotuning is an approach that explores a search space of possible implementations/configurations of a kernel or an application by selecting and evaluating a subset of implementations/configurations on a target platform and/or use models to identify a high performance implementation/configuration. In this paper, we develop an autotuning framework that leverages Bayesian optimization to explore the parameter space search. We select six of the most complex benchmarks from the application domains of the PolyBench benchmarks (syr2k, 3mm, heat-3d, lu, covariance, and Floyd-Warshall) and apply the newly developed LLVM Clang/Polly loop optimization pragmas to the benchmarks to optimize them. We then use the autotuning framework to optimize the pragma parameters to improve their performance. The experimental results show that our autotuning approach outperforms the other compiling methods to provide the smallest execution time for the benchmarks syr2k, 3mm, heat-3d, lu, and covariance with two large datasets in 200 code evaluations for effectively searching the parameter spaces with up to 170,368 different configurations. We compare four different supervised learning methods within Bayesian optimization and evaluate their effectiveness. We find that the Floyd-Warshall benchmark did not benefit from autotuning because Polly uses heuristics to optimize the benchmark to make it run much slower. To cope with this issue, we provide some compiler option solutions to improve the performance.

cs.PF↗

arXiv2020

Meta Continual Learning via Dynamic Programming

Meta continual learning algorithms seek to train a model when faced with similar tasks observed in a sequential manner. Despite promising methodological advancements, there is a lack of theoretical frameworks that enable analysis of learning challenges such as generalization and catastrophic forgetting. To that end, we develop a new theoretical approach for meta continual learning~(MCL) where we mathematically model the learning dynamics using dynamic programming, and we establish conditions of optimality for the MCL problem. Moreover, using the theoretical framework, we derive a new dynamic-programming-based MCL method that adopts stochastic-gradient-driven alternating optimization to balance generalization and catastrophic forgetting. We show that, on MCL benchmark data sets, our theoretically grounded method achieves accuracy better than or comparable to that of existing state-of-the-art methods.

cs.LG↗

arXiv2020

Dynamic Graph Neural Network for Traffic Forecasting in Wide Area Networks

Wide area networking infrastructures (WANs), particularly science and research WANs, are the backbone for moving large volumes of scientific data between experimental facilities and data centers. With demands growing at exponential rates, these networks are struggling to cope with large data volumes, real-time responses, and overall network performance. Network operators are increasingly looking for innovative ways to manage the limited underlying network resources. Forecasting network traffic is a critical capability for proactive resource management, congestion mitigation, and dedicated transfer provisioning. To this end, we propose a nonautoregressive graph-based neural network for multistep network traffic forecasting. Specifically, we develop a dynamic variant of diffusion convolutional recurrent neural networks to forecast traffic in research WANs. We evaluate the efficacy of our approach on real traffic from ESnet, the U.S. Department of Energy's dedicated science network. Our results show that compared to classical forecasting methods, our approach explicitly learns the dynamic nature of spatiotemporal traffic patterns, showing significant improvements in forecasting accuracy. Our technique can surpass existing statistical and deep learning approaches by achieving approximately 20% mean absolute percentage error for multiple hours of forecasts despite dynamic network traffic settings.

cs.LG↗

arXiv2020

Graph Neural Network Architecture Search for Molecular Property Prediction

Predicting the properties of a molecule from its structure is a challenging task. Recently, deep learning methods have improved the state of the art for this task because of their ability to learn useful features from the given data. By treating molecule structure as graphs, where atoms and bonds are modeled as nodes and edges, graph neural networks (GNNs) have been widely used to predict molecular properties. However, the design and development of GNNs for a given data set rely on labor-intensive design and tuning of the network architectures. Neural architecture search (NAS) is a promising approach to discover high-performing neural network architectures automatically. To that end, we develop an NAS approach to automate the design and development of GNNs for molecular property prediction. Specifically, we focus on automated development of message-passing neural networks (MPNNs) to predict the molecular properties of small molecules in quantum mechanics and physical chemistry data sets from the MoleculeNet benchmark. We demonstrate the superiority of the automatically discovered MPNNs by comparing them with manually designed GNNs from the MoleculeNet benchmark. We study the relative importance of the choices in the MPNN search space, demonstrating that customizing the architecture is critical to enhancing performance in molecular property prediction and that the proposed approach can perform customization automatically with minimal manual effort.

cs.LG↗

arXiv2020

Recurrent Neural Network Architecture Search for Geophysical Emulation

Developing surrogate geophysical models from data is a key research topic in atmospheric and oceanic modeling because of the large computational costs associated with numerical simulation methods. Researchers have started applying a wide range of machine learning models, in particular neural networks, to geophysical data for forecasting without these constraints. Constructing neural networks for forecasting such data is nontrivial, however, and often requires trial and error. To address these limitations, we focus on developing proper-orthogonal-decomposition-based long short-term memory networks (POD-LSTMs). We develop a scalable neural architecture search for generating stacked LSTMs to forecast temperature in the NOAA Optimum Interpolation Sea-Surface Temperature data set. Our approach identifies POD-LSTMs that are superior to manually designed variants and baseline time-series prediction methods. We also assess the scalability of different architecture search strategies on up to 512 Intel Knights Landing nodes of the Theta supercomputer at the Argonne Leadership Computing Facility.

physics.comp-ph↗

arXiv2020

Non-autoregressive time-series methods for stable parametric reduced-order models

Advection-dominated dynamical systems, characterized by partial differential equations, are found in applications ranging from weather forecasting to engineering design where accuracy and robustness are crucial. There has been significant interest in the use of techniques borrowed from machine learning to reduce the computational expense and/or improve the accuracy of predictions for these systems. These rely on the identification of a basis that reduces the dimensionality of the problem and the subsequent use of time series and sequential learning methods to forecast the evolution of the reduced state. Often, however, machine-learned predictions after reduced-basis projection are plagued by issues of stability stemming from incomplete capture of multiscale processes as well as due to error growth for long forecast durations. To address these issues, we have developed a \emph{non-autoregressive} time series approach for predicting linear reduced-basis time histories of forward models. In particular, we demonstrate that non-autoregressive counterparts of sequential learning methods such as long short-term memory (LSTM) considerably improve the stability of machine-learned reduced-order models. We evaluate our approach on the inviscid shallow water equations and show that a non-autoregressive variant of the standard LSTM approach that is bidirectional in the PCA components obtains the best accuracy for recreating the nonlinear dynamics of partial observations. Moreover---and critical for many applications of these surrogates---inference times are reduced by three orders of magnitude using our approach, compared with both the equation-based Galerkin projection method and the standard LSTM approach.

physics.comp-ph↗

arXiv2020

A Gradient-Aware Search Algorithm for Constrained Markov Decision Processes

The canonical solution methodology for finite constrained Markov decision processes (CMDPs), where the objective is to maximize the expected infinite-horizon discounted rewards subject to the expected infinite-horizon discounted costs constraints, is based on convex linear programming. In this brief, we first prove that the optimization objective in the dual linear program of a finite CMDP is a piece-wise linear convex function (PWLC) with respect to the Lagrange penalty multipliers. Next, we propose a novel two-level Gradient-Aware Search (GAS) algorithm which exploits the PWLC structure to find the optimal state-value function and Lagrange penalty multipliers of a finite CMDP. The proposed algorithm is applied in two stochastic control problems with constraints: robot navigation in a grid world and solar-powered unmanned aerial vehicle (UAV)-based wireless network management. We empirically compare the convergence performance of the proposed GAS algorithm with binary search (BS), Lagrangian primal-dual optimization (PDO), and Linear Programming (LP). Compared with benchmark algorithms, it is shown that the proposed GAS algorithm converges to the optimal solution faster, does not require hyper-parameter tuning, and is not sensitive to initialization of the Lagrange penalty multiplier.

cs.LG↗

arXiv2020

Towards On-Chip Bayesian Neuromorphic Learning

If edge devices are to be deployed to critical applications where their decisions could have serious financial, political, or public-health consequences, they will need a way to signal when they are not sure how to react to their environment. For instance, a lost delivery drone could make its way back to a distribution center or contact the client if it is confused about how exactly to make its delivery, rather than taking the action which is "most likely" correct. This issue is compounded for health care or military applications. However, the brain-realistic temporal credit assignment problem neuromorphic computing algorithms have to solve is difficult. The double role weights play in backpropagation-based-learning, dictating how the network reacts to both input and feedback, needs to be decoupled. e-prop 1 is a promising learning algorithm that tackles this with Broadcast Alignment (a technique where network weights are replaced with random weights during feedback) and accumulated local information. We investigate under what conditions the Bayesian loss term can be expressed in a similar fashion, proposing an algorithm that can be computed with only local information as well and which is thus no more difficult to implement on hardware. This algorithm is exhibited on a store-recall problem, which suggests that it can learn good uncertainty on decisions to be made over time.

cs.NE↗

arXiv2020

Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting

Highway traffic modeling and forecasting approaches are critical for intelligent transportation systems. Recently, deep-learning-based traffic forecasting methods have emerged as state of the art for a wide range of traffic forecasting tasks. However, these methods require a large amount of training data, which needs to be collected over a significant period of time. This can present a number of challenges for the development and deployment of data-driven learning methods for highway networks that suffer from lack of historical data. A promising approach to address this issue is transfer learning, where a model trained on one part of the highway network can be adapted for a different part of the highway network. We focus on diffusion convolutional recurrent neural network (DCRNN), a state-of-the-art graph neural network for highway network forecasting. It models the complex spatial and temporal dynamics of the highway network using a graph-based diffusion convolution operation within a recurrent neural network. DCRNN cannot perform transfer learning, however, because it learns location-specific traffic patterns, which cannot be used for unseen regions of the network. To that end, we develop a new transfer learning approach for DCRNN, where a single model trained on data-rich regions of the highway network can be used to forecast traffic on unseen regions of the highway network. We evaluate the ability of our approach to forecast the traffic on the entire California highway network with one year of time series data. We show that TL-DCRNN can learn from several regions of the California highway network and forecast the traffic on the unseen regions of the network with high accuracy. Moreover, we demonstrate that TL-DCRNN can learn from San Francisco region traffic data and can forecast traffic on the Los Angeles region and vice versa.

cs.LG↗

arXiv2020

Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting

Traffic forecasting approaches are critical to developing adaptive strategies for mobility. Traffic patterns have complex spatial and temporal dependencies that make accurate forecasting on large highway networks a challenging task. Recently, diffusion convolutional recurrent neural networks (DCRNNs) have achieved state-of-the-art results in traffic forecasting by capturing the spatiotemporal dynamics of the traffic. Despite the promising results, however, applying DCRNNs for large highway networks still remains elusive because of computational and memory bottlenecks. We present an approach for implementing a DCRNN for a large highway network that overcomes these limitations. Our approach uses a graph-partitioning method to decompose a large highway network into smaller networks and trains them independently. We demonstrate the efficacy of the graph-partitioning-based DCRNN approach to model the traffic on a large California highway network with 11,160 sensor locations. We develop an overlapping nodes approach for the graph-partitioning-based DCRNN to include sensor locations from partitions that are geographically close to a given partition. Furthermore, we demonstrate that the DCRNN model can be used to forecast the speed and flow simultaneously and that the forecasted values preserve fundamental traffic flow dynamics. Our approach to developing DCRNN models that represent large highway networks can be a potential core capability in advanced highway traffic monitoring systems, where a trained DCRNN model forecasting traffic at all sensor locations can be used to adjust traffic management strategies proactively based on anticipated future conditions.

cs.LG↗

arXiv2020

Determining feature importance for actionable climate change mitigation policies

Given the importance of public support for policy change and implementation, public policymakers and researchers have attempted to understand the factors associated with this support for climate change mitigation policy. In this article, we compare the feasibility of using different supervised learning methods for regression using a novel socio-economic data set which measures public support for potential climate change mitigation policies. Following this model selection, we utilize gradient boosting regression, a well-known technique in the machine learning community, but relatively uncommon in public policy and public opinion research, and seek to understand what factors among the several examined in previous studies are most central to shaping public support for mitigation policies in climate change studies. The use of this method provides novel insights into the most important factors for public support for climate change mitigation policies. Using national survey data, we find that the perceived risks associated with climate change are more decisive for shaping public support for policy options promoting renewable energy and regulating pollutants. However, we observe a very different behavior related to public support for increasing the use of nuclear energy where climate change risk perception is no longer the sole decisive feature. Our findings indicate that public support for renewable energy is inherently different from that for nuclear energy reliance with the risk perception of climate change, dominant for the former, playing a subdued role for the latter.

stat.OT↗