SUOD accelerates OD for large, diverse models.
problem Training and scoring new samples with many unsupervised, heterogeneous OD models.
method Data reduction, model approximation, and taskload optimization.
result SUOD accelerates OD for over 20 benchmark datasets and a real-world case.
Paper proposes NASAIC framework for co-designing neural architectures and heterogeneous ASICs.
problem Designing efficient neural architectures and ASICs for multiple tasks.
method Build ASIC templates and propose NASAIC framework for simultaneous design of architectures and ASICs.
result NASAIC ensures design specifications and maximizes accuracy with minimal performance loss.
Minibatch SGD outperforms Local SGD in heterogeneous distributed learning.
problem Optimizing a combined convex objective with stochastic gradient estimates from different machines.
method Analysis of Minibatch SGD and Local SGD in a heterogeneous distributed setting.
result Minibatch SGD dominates Local SGD in the heterogeneous distributed setting.
Proposes EDM algorithm to accelerate model training in distributed networks.
problem Hindered effectiveness of distributed stochastic optimization algorithms due to data heterogeneity and network sparsity.
method Introduces Exact-Diffusion with Momentum (EDM) algorithm, incorporating momentum techniques to mitigate bias and enhance convergence rate.
result EDM algorithm converges sub-linearly to the optimal solution, radius independent of data heterogeneity, for non-convex objective functions.
Memory bandwidth bottleneck is a major challenges in processing machine learning (ML) algorithms. In-memory acceleration has potential to address this problem; however, it needs to address two challenges. First, in-memory accelerator should be general enough to support a large set of different ML algorithms. Second, it…
New method identifies subgroups in censored data.
problem Identifying meaningful patterns in heterogeneous populations.
method Combining inverse probability weighting, M-estimation, and concave pairwise fusion penalization.
result Robust approach for censored data under heterogeneous AFT models.
We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute accelerators such as GPUs and FPGAs for the training of large-scale machine learning models, when the training data exceeds their memory cap…
Novel framework identifies pump-specific deterioration rates using Bayesian hierarchical hazard modeling and causal discovery.
problem Challenges in asset management due to heterogeneous deterioration rates in pump equipment.
method Bayesian hierarchical hazard modeling with causal discovery, GPU-accelerated No-U-Turn Sampling (NUTS), and DirectLiNGAM.
result Identified striking heterogeneity in deterioration rates, with negative effects 400 times larger than positive effects.
Scaff-PD improves fairness and robustness in federated learning with reduced communication.
problem Improving fairness and robustness in federated learning with limited communication.
method Scaff-PD uses a family of distributionally robust objectives and an accelerated primal dual algorithm with bias-corrected steps.
result Scaff-PD achieves significant gains in communication efficiency and convergence speed while maintaining fairness and robustness.
RAPTOR-GEN accelerates digital twin development for biopharmaceuticals.
problem Lack of agility in rapid, on-demand production of biotherapeutics due to bioprocess complexity.
method Bayesian learning framework based on a multi-scale probabilistic knowledge graph (pKG) and stochastic differential equations (SDE).
result RAPTOR-GEN accelerates intelligent digital twin development from sparse and heterogeneous experimental data.
This paper uses machine learning to select kernels for machine learning models on various devices.
problem Traditional kernel auto-tuning is limited for machine learning research with changing network topologies and hyperparameters.
method Combines auto-tuning and machine learning to select kernels for SYCL on various devices.
result Initial results show high performance kernel selection with little developer effort.
Paper shows local SGD outperforms mini-batch SGD under certain conditions.
problem Proving local SGD's superiority in distributed learning with heterogeneous data.
method New lower and upper bounds for local SGD under first-order heterogeneity assumptions.
result Local SGD is min-max optimal under certain conditions, resolving understanding of distributed optimization.
This paper optimizes how deep learning models are distributed across different devices.
problem Optimizing how large, complex neural networks are split across multiple devices.
method Identified and solved an optimization problem for device placement of DNN operators.
result Automated algorithms that solve the device placement problem for modern pipelined settings.
Fault-tolerant federated learning for non-uniform data.
problem Faulty workers corrupting data in federated learning.
method Fault-resilient proximal gradient (FRPG) algorithm with Nesterov's acceleration and local FRPG for reduced communication.
result FRPG and LFRPG converge faster than robust stochastic aggregation.
EM algorithm speeds up convergence in federated learning with heterogenous data.
problem Understanding convergence rates of federated learning algorithms under data heterogeneity.
method Characterized convergence rate of EM algorithm for FMLR model under various regimes.
result EM algorithm converges to ground truth with SNR ≥ √K in all regimes.
TSVQR captures heterogeneous and asymmetric data using quantile regression.
problem Capturing heterogeneous and asymmetric information in modern data.
method Twin Support Vector Quantile Regression (TSVQR) with two nonparallel planes for quantile levels.
result TSVQR outperforms previous methods in capturing and learning from data.
Adaptive sampling improves convergence in heterogeneous distributed optimization.
problem Poor performance of classical SGD and SVRG in heterogeneous distributed settings.
method Adaptive sampling of machines with an adaptive estimate of local Lipschitz constants.
result Significantly accelerates convergence rate from maximum to average Lipschitz constant.
PCL tackles collaborative learning for diverse agents, reducing sample complexity.
problem Balancing collaborative speedup with personalization for heterogeneous agents.
method AffPCL, with bias and importance correction mechanisms.
result AffPCL reduces sample complexity by a factor of max{n−1,δ}, where n is the number of agents and δ∈[0,1] measures heterogeneity. Recent technological advances have proliferated the available computing power, memory, and speed of modern Central Processing Units (CPUs), Graphics Processing Units (GPUs), and Field Programmable Gate Arrays (FPGAs). Consequently, the performance and complexity of Artificial Neural Networks (ANNs) is burgeoning. While…
FedCluster accelerates federated learning convergence by cycling device groups.
problem Federated learning convergence issues with device-level data heterogeneity.
method FedCluster groups devices into clusters that cycle through learning rounds, boosting convergence with meta-updates.
result FedCluster achieves faster convergence in nonconvex optimization compared to FedAvg.
Study improves machine learning for estimating survival treatment effects.
problem Estimating heterogeneous survival treatment effects in observational data.
method Flexible machine learning methods in the counterfactual framework, including AFT-BART-NP.
result AFT-BART-NP consistently yields best performance in terms of bias, precision, and frequentist coverage.
The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms, high-performance 3D manycore platforms that incorporate both CPUs and GPUs present a pr…
Paper proposes an efficient online Newton method with Nesterov's acceleration for streaming data.
problem Efficient inference of online Newton methods with robustness to noise and ill-conditioning.
method Online Newton method with Hessian averaging and Nesterov's accelerated sketch-and-project solver.
result Global almost-sure convergence and asymptotic normality of the last iterate with non-asymptotic convergence guarantees.
FedGLOMO accelerates FL convergence for non-convex functions.
problem Efficiently solving non-convex optimization problems in federated learning with client heterogeneity.
method Combines global and local momentum updates to reduce variance and improve convergence rate.
result Achieves O(ε−1.5) convergence to ε-stationary point, compared to O(ε−2). A new validation scheme improves Federated Learning performance.
problem Learning a joint model from distributed, heterogeneous data.
method DVW scheme that uses distributed validation sets.
result DVW outperforms FedAvg in heterogeneous environments.
New projection techniques reduce the frequency of projections in solving LCPs.
problem Solving linearly constrained problems efficiently with reduced projection frequency.
method Delayed projection technique to call a projection less frequently.
result Theoretical and practical improvements in convergence rates and efficiency.
Ringmaster LMO accelerates training in distributed systems by asynchronously updating neural networks.
problem Asynchronous training in distributed systems where workers compute gradients at different speeds.
method Introduces an asynchronous LMO-based momentum method for unconstrained stochastic nonconvex optimization.
result Establishes convergence guarantees and time complexity bounds for asynchronous LMO-based updates.
A new method for online personalized learning reduces gradient variance by dynamically selecting peers.
problem Online personalized decentralized learning with statistically heterogeneous clients.
method Gradient-based collaboration criterion allowing clients to dynamically select peers with similar gradients.
result The method acts as a variance reduction method, achieving optimal performance in certain conditions.
BEER accelerates decentralized nonconvex optimization to O(1/T) rate.
problem Communication bottleneck in decentralized machine learning.
method Communication-compressed algorithm with gradient tracking.
result Converges at O(1/T) rate, matching uncompressed performance. ChemCPA predicts cellular responses to novel drugs using transfer learning.
problem Scaling high-throughput screens to measure cellular responses for many drugs is costly and challenging.
method ChemCPA, a new encoder-decoder architecture combined with transfer learning.
result Training on existing bulk RNA HTS datasets improves generalization performance, reducing the need for extensive single-cell screens.
Efficiently calculates privacy guarantees for 2020 Census data.
problem Evaluate privacy guarantees for 2020 U.S. Census data releases.
method Sieve-accelerated quadrature method to evaluate tail probabilities of high-dimensional convolutions.
result Achieves 1,824-fold speedup over prior methods while maintaining error tolerances.
Event-based learning reduces communication in distributed networks.
problem Distributed learning with diverse data distributions and communication inefficiencies.
method A distributed learning algorithm using ADMM with event-triggered communication.
result The algorithm converges even with distinct local data distributions and achieves accelerated convergence in convex settings.
ATA optimizes task allocation in distributed machine learning.
problem Greedy task allocation leads to inefficiencies in distributed machine learning.
method Adaptive Task Allocation (ATA) adapts to unknown computation time distributions.
result ATA identifies optimal task allocation without prior knowledge of computation times.
Study reveals investor behavior in NFT bubbles.
problem Understanding retail investor behavior in asset bubbles.
method Systematic study of NFTs using public blockchain data.
result Sophisticated investors outperform others in NFT bubbles.
JaxMARL-HFT accelerates MARL for HFT with 240x speedup.
problem Heavy computational cost in MARL for HFT.
method GPU-accelerated JAX framework for multi-agent RL.
result Agents learn to outperform benchmarks in HFT.
A new method boosts survival analysis by stratifying patients and removing noise covariates.
problem Weak detection of treatment differences in randomized clinical trials due to patient heterogeneity.
method 5-Step Stratified Testing and Amalgamation Routine (5-STAR) using elastic net Cox regression and conditional inference trees.
result The 5-STAR routine significantly improves power in detecting treatment effects compared to traditional methods.
New method FedEx accelerates federated hyperparameter tuning.
problem Federated hyperparameter tuning challenges in distributed learning.
method FedEx method connecting to weight-sharing, adapted for federated optimization.
result FedEx outperforms natural baselines on various benchmarks.
PRISM integrates diverse rewards in MORL, improving sample efficiency and Pareto coverage.
problem Heterogeneous MORL where dense objectives dominate, leading to poor sample efficiency.
method PRISM uses reflectional symmetry and ReSymNet to reconcile temporal-frequency mismatches and accelerate exploration.
result PRISM consistently outperforms sparse-reward baselines and oracles, achieving significant Pareto gains.
Enhanced volatility forecasting using options data and rough volatility model.
problem Improving realized volatility forecasting accuracy.
method Infer spot volatility from options data using rough stochastic volatility model, accelerate estimation with deep learning, benchmark against traditional models.
result Augmented HAR-RV-RHeston model outperforms traditional models in daily and long-term forecasting.
Integrated Computational Materials Engineering (ICME) aims to accelerate optimal design of complex material systems by integrating material science and design automation. For tractable ICME, it is required that (1) a structural feature space be identified to allow reconstruction of new designs, and (2) the reconstructi…
FedAMD framework improves federated learning with partial client participation.
problem Data heterogeneity and inactive client updates in partial client participation.
method Anchor sampling divides clients into anchor and miner groups, using large and small batches respectively.
result FedAMD achieves faster convergence and improved model performance compared to state-of-the-art methods.
Study causal financial signals for non-stationary markets, improving short-term forecasts.
problem Short-term forecasting in non-stationary financial markets under causal constraints.
method Construct causal signals from heterogeneous micro-features using causal centering, linear aggregation, Kalman filter, and forward-like operator.
result Causally constructed observables can exhibit substantial economic relevance in specific regimes but degrade under regime shifts.
Specialized Deep Learning (DL) acceleration stacks, designed for a specific set of frameworks, model architectures, operators, and data types, offer the allure of high performance while sacrificing flexibility. Changes in algorithms, models, operators, or numerical systems threaten the viability of specialized hardware…
SA-PEF improves federated learning efficiency by correcting gradient mismatches.
problem Slow decay of residual error in federated learning under non-IID data.
method Integrates step-ahead correction with partial error feedback.
result Achieves faster convergence and target accuracy compared to standard EF.
Proposes a new AFT model for nonlinear survival data.
problem Limited ability of classical AFT models to represent nonlinear relationships and handle complex covariate structures.
method Structured nonparametric extension using Kolmogorov--Arnold representations and unified censoring-adjusted losses.
result Method captures nonlinear effects and recovers linear structure when appropriate.
The ever-increasing demand from mobile Machine Learning (ML) applications calls for evermore powerful on-chip computing resources. Mobile devices are empowered with heterogeneous multi-processor Systems-on-Chips (SoCs) to process ML workloads such as Convolutional Neural Network (CNN) inference. Mobile SoCs house sever…
Accelerates Riemannian gradient methods with extrapolation.
problem Optimizing functions on manifolds efficiently.
method Extrapolating iterates in Riemannian gradient descent.
result Achieves optimal convergence rate and computational advantage.
UK's rapid vaccine rollout linked to reduced COVID-19 mortality.
problem Assessing the impact of accelerated vaccine rollout on public health outcomes.
method Flexible probabilistic models combining interrupted time series analysis and synthetic control methods with multi-output Gaussian processes.
result Substantial reduction in COVID-19 mortality with little effect on transmission rates.