Paper explores weighted averaging schemes for SGD, achieving asymptotic normality and optimality.
problem Improving convergence of SGD in various settings.
method Develops a general weighted averaging scheme for SGD and establishes asymptotic normality.
result Establishes asymptotic normality and optimality of weighted averaged SGD solutions.
This paper analyzes SGD with increasingly weighted averaging for optimization and generalization.
problem Improving optimization and generalization for non-strongly convex objectives.
method Comprehensive analysis of increasingly weighted averaging schemes for convex, strongly convex, and non-convex objectives.
result The weight α affects both optimization and generalization errors, revealing a trade-off. WASH trains ensembles with shuffled weights to improve accuracy and reduce communication.
problem Training ensembles for weight averaging leads to models converging to different loss basins.
method WASH randomly shuffles a small percentage of weights during training to keep models within the same basin.
result WASH achieves state-of-the-art image classification accuracy with lower communication costs.
New moving average adapts weight dynamically based on polynomial and wavefunction.
problem Lagging traditional moving averages in adjusting to changes in data.
method Develops a moving average with weight as a polynomial of a wavefunction from an eigenproblem.
result Immediate 'switch' without lag, adapting to changes in data.
Unified analysis of finite weight averaging methods in deep learning.
problem Theoretical explanation of finite weight averaging methods in deep learning.
method Generalized SGD and LAWA, establishing convergence and generalization bounds.
result FWA achieves faster convergence and better generalization compared to SGD.
A new method for averaging model predictions using minimum divergence.
problem Improving model averaging methods, especially in small samples.
method Minimum divergence framework for model weight calculation.
result Empirically outperforms standard model averaging methods.
Paper introduces stability in model averaging and proposes a L2-penalty method.
problem Theoretical properties of model averaging from stability perspective.
method Introduces stability, defines asymptotic empirical risk minimizer, and proposes L2-penalty model averaging method.
result Proposed L2-penalty method ensures stability and consistency under reasonable conditions.
This study optimizes model averaging for personalized collaborative learning.
problem Differences in data or objectives between nodes in federated learning.
method Weighted averaging between local and global models for scalar mean estimation.
result There is always some positive model averaging that reduces expected squared error.
Optimal weight windows are found by projecting the origin onto a convex polytope.
problem Finding the best weight windows for a weighted moving average smoother.
method Formulated as a quadratic program and projection onto a convex polytope.
result Optimal weight windows are symmetrical and decrease in weight away from the center.
SWAP uses large mini-batches to train DNNs faster with good generalization.
problem Training deep neural networks with small mini-batches is time-consuming.
method SWAP computes an approximate solution with large mini-batches and refines it by averaging weights of multiple parallel models.
result SWAP trains models as well as small-batch training but in significantly less time.
Improved averaging method for noisy observations converges strongly.
problem Noisy observations from random dynamical systems require stable estimates.
method Introduced p-EMA, a modified exponential moving average with subharmonic weight decay. result Stochastic convergence guarantees for p-EMA under mild assumptions. In mixture model-based clustering applications, it is common to fit several models from a family and report clustering results from only the `best' one. In such circumstances, selection of this best model is achieved using a model selection criterion, most often the Bayesian information criterion. Rather than throw awa…
BayesBlend blends multiple models' predictions for better insurance loss predictions.
problem Improving insurance loss predictions by combining multiple models.
method Pseudo-Bayesian model averaging, stacking, and hierarchical stacking.
result BayesBlend provides a user-friendly way to blend model predictions and estimate weights.
Distributed learning for related tasks using graph weights.
problem Learning multiple tasks on different machines.
method Weighted averaging of messages with skewing or stepsize control.
result Different tasks can be learned on different machines.
New class of heavy-tailed distributions shows weighted averages dominate individual variables.
problem Understanding and comparing risks in heavy-tailed distributions.
method Introducing a new class of heavy-tailed distributions and proving stochastic dominance relations.
result Weighted averages of random variables in this class are stochastically larger than individual variables.
New method improves semi-supervised learning by averaging weights.
problem Improving semi-supervised learning performance with limited labeled data.
method Stochastic Weight Averaging (SWA) and fast-SWA to train consistency-based models.
result Achieved best semi-supervised results on CIFAR-10 and CIFAR-100 datasets.
Improves random survival forest model by weighted averaging.
problem Improving the performance of random survival forest.
method Modifies random forest by weighted averaging of trees, optimizing weights via quadratic optimization to maximize Harrell's C-index.
result The weighted random survival forest outperforms the original model in numerical examples.
A new averaging scheme improves stochastic gradient methods.
problem Improving the performance of stochastic gradient descent.
method Proposes a weighted averaging scheme with decaying weights.
result The method has a regularizing effect equivalent to ridge regression.
The study introduces anytime learning schedules for large language models without fixed horizons.
problem Training large language models without knowing the total training horizon.
method Theoretical analysis and weight averaging to create anytime learning schedules.
result Theoretical and empirical evidence shows that weight averaging with simple step sizes can achieve comparable final loss to well-tuned cosine schedules.
SQWA improves low-precision DNNs with model averaging and quantization.
problem Designing good generalization DNNs with quantized weights.
method Floating-point model training, direct quantization, multiple low-precision models, weight averaging, re-quantization, fine-tuning, loss visualization.
result State-of-the-art results for 2-bit QDNNs on CIFAR-100 and ImageNet datasets.
The paper offers methods to price complex options using upper and lower bounds.
problem Pricing complex options like Asian and basket options.
method Develops a general framework using lower and upper bounds.
result Lower bounds simplify the problem and provide reasonable approximations.
This paper studies distributed linear regression by averaging to reduce communication costs.
problem Reducing communication costs in distributed statistical learning with large datasets.
method One-step and iterative weighted parameter averaging in statistical linear models under data parallelism.
result The method reduces performance loss in estimation, test error, and confidence interval length compared to full data regression in high dimensions.
Averaging recent model checkpoints speeds up training time.
problem Training large vision or language models is time-consuming.
method Average the weights of the k latest checkpoints.
result Speeds up training by dozens of epochs, saving up to 68 GPU hours.
Enhances trading signals using image analysis and weighted moving averages.
problem Improving price trend trading strategies in financial markets.
method Image-induced importance weights applied to weighted moving averages of trading signals.
result Significant enhancement of price trend trading signals with improved portfolio selection.
Develops KOM method for optimal GATE estimation.
problem Causal effect estimation sensitivity to model misspecification and practical violations of positivity.
method Kernel Optimal Matching (KOM) for optimal GATE estimation.
result KOM provides uniform control over conditional mean squared error and precision.
The paper extends a prediction method to curved spaces.
problem Prediction with expert advice in curved spaces.
method Geometric considerations and adaptation of online to batch conversion.
result Extension of exponentially weighted average forecaster to non-positive curvature spaces.
A new RNN model computes a recurrent weighted average over past processing steps, outperforming standard LSTM models.
problem Handling sequential data with limited information from previous steps.
method Proposes a new RNN model that computes a recurrent weighted average (RWA) over every past processing step.
result The RWA model outperforms standard LSTM models on various tasks.
Proposes a non-convex optimization method for a parsimonious weighted naive Bayes classifier.
problem Improving naïve Bayes classifier performance with a large number of input variables.
method Sparse regularization of model log-likelihood for direct estimation of variable weights.
result Optimization-based weighted naïve Bayes classifiers achieve equivalent performance to averaging-based classifiers.
Averaging SGD weights improves deep learning models.
problem Improving deep learning model generalization.
method Simple averaging of SGD weights with cyclical or constant learning rate.
result SWA leads to better generalization and flatter solutions.
Optimal model averaging for conditional generative models improves performance across various data types.
problem Multiple plausible generators for conditional distributions can vary in performance.
method Sample-based maximum mean discrepancy, static model averaging, and mixture-of-experts model averaging.
result MoEMA improves over competing baselines across various data types.
Bayesian stacking improves model performance with varying model weights.
problem Improving model predictions with heterogeneous input performance.
method Bayesian hierarchical stacking with varying model weights inferred via Bayesian inference.
result Hierarchical stacking yields better predictions than linear averaging.
clusterBMA combines clustering results from multiple models using Bayesian model averaging.
problem Uncertainty in model selection for clustering.
method Bayesian model averaging to combine results from multiple clustering algorithms.
result ClusterBMA offers probabilistic cluster allocations and quantifies model-based uncertainty.
SWALP averages SGD iterates for low-precision training, improving scalability and performance.
problem Improving scalability and performance in low-precision training.
method Averages low-precision SGD iterates with a modified learning rate schedule.
result SWALP matches full-precision SGD performance with 8-bit quantization and converges to optimal solutions.
Simplified analysis of SGD for linear regression with weight averaging.
problem Understanding SGD optimization in linear regression models.
method Simplified analysis using linear algebra tools, bypassing complex operator manipulations.
result Recovery of bias and variance bounds for SGD in linear regression.
Federated learning technique improves convergence speed with communication delays.
problem Communication delays between edge nodes and aggregator in federated learning.
method Developed FedDelAvg, a technique that generalizes federated averaging to incorporate a weighting between current local model and delayed global model.
result FedDelAvg achieves a significant improvement in convergence speed, especially when optimizing the weighting scheme to account for delays.
We introduce a covariance matrix estimator that both takes into account the heteroskedasticity of financial returns (by using an exponentially weighted moving average) and reduces the effective dimensionality of the estimation (and hence measurement noise) via techniques borrowed from random matrix theory. We calculate…
This paper studies robust estimation methods in high dimensions, comparing model-averaged and composite quantile estimators.
problem Understanding robustness in high-dimensional regularized estimation.
method Optimal weights are determined by minimizing the asymptotic mean squared error, incorporating regularization effects without perfect selection.
result Model-averaged and composite quantile estimators often outperform least-squares methods in prediction quality.
Extends double linear policy with time-varying weights and proves robust positive expectation.
problem Ensuring robustness in policy optimization with time-varying parameters.
method Employed a novel elementary symmetric polynomials characterization approach to prove robust positive expectation (RPE). Derived explicit expressions for expected cumulative gain-loss and variance.
result Proved the robust positive expectation property holds for the extended double linear policy.
New bounds for average graph distance using curvature and centrality.
problem Finding bounds for average graph distance.
method Using weighted average Ollivier curvature with edge betweenness centrality.
result Equality in bounds achieved for specific reflective graphs.
Bayesian model averaging improves causal effect estimation by averaging over multiple models.
problem Estimating causal effects under linear Structural Causal Models (SCMs).
method Bayesian model averaging using Gaussian scale mixture distributions for computational efficiency.
result Bayesian model averaging is optimal for causal effect estimation.
Kernel balancing weights are generalized as KRRR, providing better confidence intervals for treatment effects.
problem Lack of generalization error, correct feature specification, and limited to average effects.
method Interpreting kernel balancing weights as KRRR, relaxing feature specification, and extending Gaussian approximation.
result KRRR provides strong generalization properties and justifies confidence sets for causal functions.
Optimizes sample weights for representative data averages.
problem Achieving sample averages close to prescribed values.
method Formulates as an optimization problem, often convex and efficiently solvable.
result Heuristic methods based on convex optimization perform well.
Improved neural networks by averaging late-stage weights.
problem Improving the performance of neural networks.
method Ensemble late-stage weights and average them.
result Augmenting standard models with late-phase weights improves generalization.
The paper examines how random seed affects model stability and proposes ASWA and NASWA techniques to improve model robustness.
problem The impact of random seed on model performance and stability.
method A controlled study on attention, gradient-based, and surrogate model interpretations. Proposed techniques: Aggressive Stochastic Weight Averaging (ASWA) and Norm-filtered Aggressive Stochastic Weight Averaging (NASWA).
result Improvement in model robustness with ASWA and NASWA techniques, reducing standard deviation of model performance by 72%.
This paper solves aggregation of Pareto optimal models by using Bayesian priors and weighted averaging.
problem How to rationally aggregate Pareto optimal models while preserving Pareto efficiency.
method Four logical steps: 1) Bayesian models, 2) Prior as preference ranking, 3) Consistent aggregation, 4) Weighted average of priors.
result All rational/consistent aggregation rules follow a generalized hierarchical Bayesian model.
This paper investigates robust and efficient DR/RDR estimators for WATEs.
problem Lack of systematic investigation into robustness and efficiency conditions for WATE estimation.
method Proposes three RDR estimators using semiparametric efficient influence function and double/debiased machine learning.
result Demonstrates the practical relevance of the methods in medical and social sciences.
Study mass transport in low-diffusivity using Lagrangian coordinates.
problem Mass preserving transport of passive tracers in low-diffusivity limit.
method Lagrangian coordinates, time-averaged diffusion equation, weighted manifold structure.
result Leading order asymptotics extend to dominant nontrivial singular value in low-diffusivity limit.
In this note, we present a new averaging technique for the projected stochastic subgradient method. By using a weighted average with a weight of t+1 for each iterate w_t at iteration t, we obtain the convergence rate of O(1/t) with both an easy proof and an easy implementation. The new scheme is compared empirically to…