New analysis shows surprising results on adaptation speed of causal models.
problem Investigate the adaptation speed of causal models under interventions.
method Use convergence rates from stochastic optimization to measure adaptation speed.
result Surprising findings: anticausal model can be faster than causal model under certain conditions.
AdaScale SGD adapts learning rates for large-batch training efficiently.
problem Adapting learning rates for large-batch training to balance speed-ups and model quality.
method Adaptive learning rate adaptation based on gradient variance.
result AdaScale achieves reliable speed-ups for a wide range of batch sizes without degrading model quality.
Adaptive sampling improves graph diffusion models by maintaining uniform information speed.
problem Standard diffusion models overlook non-homogeneous dynamics on complex manifolds.
method Information-geometric framework using Fisher-Rao metric and Drift Variation Score (DVS).
result DVS solver ensures uniform rate of distributional change, improving structural fidelity and efficiency.
Adaptive workflow combines fast amortized inference with MCMC for many datasets.
problem Trade-off between computational speed and sampling accuracy in Bayesian inference.
method Adaptive workflow integrating amortized inference and MCMC with principled diagnostics.
result Efficiency gains with high posterior quality on tens of thousands of datasets.
Improves distributed SGD convergence speed with reduced computation load.
problem Mitigating stragglers in distributed SGD to speed up convergence.
method Modeling communication and computation times, adapting number of workers and computation load dynamically.
result Significantly reduces computation load while improving convergence speed.
Laprop separates Adam's momentum and adaptivity to improve stability and speed.
problem Unnecessary coupling between Adam's momentum and adaptivity leads to instability and divergence.
method Proposes Laprop, a method that decouples momentum and adaptivity.
result Laprop consistently improves speed and stability over Adam on various tasks.
Background-Foreground classification is a well-studied problem in computer vision. Due to the pixel-wise nature of modeling and processing in the algorithm, it is usually difficult to satisfy real-time constraints. There is a trade-off between the speed (because of model complexity) and accuracy. Inspired by the reject…
Improved LoRA+ adapts large models more efficiently.
problem Suboptimal feature learning in LoRA for large models.
method Different learning rates for LoRA adapter matrices A and B.
result Improves performance and speed by 1-2% and up to 2X, respectively.
FLAP adapts policies quickly to new tasks using shared linear representations.
problem Adapting policies to new tasks efficiently and effectively.
method FLAP uses a shared linear representation and a separate adapter network for quick adaptation.
result FLAP achieves up to 8X faster adaptation and significantly better performance on out-of-distribution tasks.
Physics-informed neural network identifies and characterizes surface cracks in metals.
problem Identifying and characterizing surface-breaking cracks in metals using ultrasound.
method Physics-informed neural network (PINN) trained with ultrasonic surface wave data and adaptive activation functions.
result PINN accurately estimates the speed of sound and identifies crack locations in metals.
A new Riemannian framework optimizes LoRA for faster convergence and better performance.
problem Optimizing low-rank adapters in neural networks to improve convergence and performance.
method Integrates Riemannion optimizer, LoRA initialization, and efficient implementation for geometrically treating low-rank adapters.
result Consistent and noticeable improvements in convergence speed and final task performance over standard LoRA and its modifications.
Random walk speed on Teichmüller space is a proper function.
problem Understanding the speed of random walks on Teichmüller space.
method Adaptation of Gouëzel's pivoting techniques to Teichmüller space.
result Speed of random walk is a proper function on Teichmüller space.
ABO extends RLS for online learning in non-stationary time-series, improving accuracy and speed.
problem Online learning in non-stationary time-series with overparameterized models.
method QR-based exponentially weighted RLS algorithm with orthogonal-triangular updates.
result ABO maintains bounded residuals and stable condition numbers while achieving speed improvements.
Improves posterior approximation speed for Dirichlet process mixture models.
problem Inefficiency of stochastic variational inference in large datasets.
method Uses stochastic gradient ascent with adaptive stepsize optimization.
result Adaptive stepsize improves speed and performance of posterior approximation.
We provide a model to understand how adverse weather conditions modify traffic flow dynamic. We first prove that the microscopic Free Flow Speed of the vehicles is changed and then provide a rule to model this change. For this, we consider a thresholded linear model, corresponding to an application of a MARS model to r…
Localizes curvature estimates for evolving hypersurfaces under various flows.
problem Establishing curvature estimates for evolving hypersurfaces under different flow conditions.
method Adapted localization of Huisken--Stampacchia iteration method to fully nonlinear flows.
result Asymptotically sharp curvature pinching estimates for general flows.
A lightweight framework improves convergence and stability of PINNs for complex PDEs.
problem Training instability and reduced accuracy in PINNs for complex PDEs.
method Adaptive curvature correction using secant information to optimize first-order optimizers.
result Consistent improvements in convergence speed, stability, and accuracy over standard optimizers.
New method combines model forecasts and real-time observations for hourly wind speed predictions.
problem Filling the six-hour gap between weather model runs for accurate hourly wind speed forecasts.
method Combines quasi-real-time observed wind speed and weather model predictions using a novel Ensemble Model Output Statistics (EMOS) strategy.
result Successfully improved wind speed predictions compared to observed data from SYNOP stations.
Stochastic Gradient Langevin Dynamics infuses isotropic gradient noise to SGD to help navigate pathological curvature in the loss landscape for deep networks. Isotropic nature of the noise leads to poor scaling, and adaptive methods based on higher order curvature information such as Fisher Scoring have been proposed t…
sGBM speeds up gradient boosting by parallelizing and adapting base learners.
problem Infeasibility of parallelizing GBM training and sub-optimal performance in online settings.
method Integrates multiple differentiable base learners, jointly optimizing them with linear speed-up.
result sGBM achieves higher time efficiency and better accuracy than traditional GBM.
Paper reinterprets ARP algorithm and improves its analysis and speed.
problem Column subset selection in data analysis.
method Volume sampling and active learning connections, new analysis, rejection sampling.
result Faster implementations and new analysis for ARP algorithm.
We introduce a gradient-based learning method to automatically adapt Markov chain Monte Carlo (MCMC) proposal distributions to intractable targets. We define a maximum entropy regularised objective function, referred to as generalised speed measure, which can be robustly optimised over the parameters of the proposal di…
Large-scale machine learning training, in particular distributed stochastic gradient descent, needs to be robust to inherent system variability such as node straggling and random communication delays. This work considers a distributed training framework where each worker node is allowed to perform local model updates a…
We present a dual subspace ascent algorithm for support vector machine training that respects a budget constraint limiting the number of support vectors. Budget methods are effective for reducing the training time of kernel SVM while retaining high accuracy. To date, budget training is available only for primal (SGD-ba…
AdaptiveLRF adapts low-rank factorization for neural networks to improve generalization without sacrificing accuracy.
problem Overfitting in neural networks, especially in shallow and deep models.
method Adaptive Low-Rank Factorization (LRF) applied to neural network layers based on their complexity.
result AdaptiveLRF improves generalization without significantly decreasing training speed or accuracy.
Study shows time matters in automated trading, improving simple strategies over complex ones.
problem Effects of reaction speed and trading urgency on automated trading strategies.
method Simulated financial markets with public limit order book and continuous double auction matching. Examined reaction speed and trading urgency.
result Simple strategies outperform complex ones when considering reaction speed and trading urgency.
Adaptive batching improves Gaussian process surrogates for noisy level set estimation.
problem Learning the level set of noisy simulator responses.
method Developed four novel adaptive batching schemes for Gaussian process metamodels.
result Adaptive batching brings significant computational speed-ups with minimal loss of modeling fidelity.
One of the main obstacles to broad application of reinforcement learning methods is the parameter sensitivity of our core learning algorithms. In many large-scale applications, online computation and function approximation represent key strategies in scaling up reinforcement learning algorithms. In this setting, we hav…
The practical performance of online stochastic gradient descent algorithms is highly dependent on the chosen step size, which must be tediously hand-tuned in many applications. The same is true for more advanced variants of stochastic gradients, such as SAGA, SVRG, or AdaGrad. Here we propose to adapt the step size by …
Federated Learning speeds up speech recognition training by 7x and reduces error rate by 6%.
problem Training acoustic models for speech recognition tasks in a federated manner.
method Hierarchical optimization and dynamic gradient aggregation methods.
result Significant improvement in training convergence speed and model performance.
Improves forecast calibration for extreme events using modified loss functions.
problem Improperly specified models do not issue calibrated forecasts for extreme events.
method Adapting loss functions based on weighted scoring rules and tail miscalibration regularization.
result Calibrated forecasts for extreme wind speeds can be improved by suitable adaptations to the loss function during model training.
New approach speeds up DNA sequence alignment.
problem Efficiently estimating alignment scores for large sets of reads.
method Rank-one crowdsourcing models and multi-armed bandit algorithm.
result Adaptive algorithm identifies pairs with large alignment scores.
Adaptive algorithm for multi-objective optimization with binary constraints.
problem Optimization of black-box problems with binary constraints.
method Bayesian optimization using regression and classification models.
result Significantly faster expected hypervolume calculation.
A new algorithm speeds up elliptical slice sampling for truncated multivariate normals.
problem Efficiently sampling from truncated multivariate normal distributions with linear constraints.
method Adapting elliptical slice sampling to linearly truncated multivariate normals, with an algorithm for ellipse-polytope intersection in O(m log m) time.
result The algorithm enhances numerical stability, speeds up running time, and is easy to parallelize.
Selecting input variables or design points for statistical models has been of great interest in adaptive design and active learning. Motivated by two scientific examples, this paper presents a strategy of selecting the design points for a regression model when the underlying regression function is discontinuous. The fi…
Adaptive model learns from time series data with changing distributions.
problem Predicting time series data under distribution shift.
method Formulates distribution shift as weighted empirical risk minimization. Uses a gradient-based learning method for a forgetting mechanism.
result Proposes an efficient method for adaptive time series prediction.
Sensors which use electromagnetic induction (EMI) to excite a response in conducting bodies have long been investigated for subsurface explosive hazard detection. In particular, EMI sensors have been used to discriminate between different types of objects, and to detect objects with low metal content. One successful, p…
This work improves autonomous racing by creating diverse opponents and adapting risk.
problem Balancing performance and safety in autonomous racing environments.
method Developed a self-play method using replica-exchange Markov chain Monte Carlo for diverse opponents and a distributionally robust bandit optimization for adaptive risk adjustment.
result Demonstrated real-time motion-planning methods achieving speeds comparable to Formula One racecars.
Computing the Wasserstein barycenter of a set of probability measures under the optimal transport metric can quickly become prohibitive for traditional second-order algorithms, such as interior-point methods, as the support size of the measures increases. In this paper, we overcome the difficulty by developing a new ad…
FedLion improves Federated Learning by speeding up convergence and reducing communication costs.
problem Slow convergence and high communication costs in Federated Learning.
method Integrates Lion's adaptive approach into Federated Learning framework, using signed gradients.
result FedLion outperforms existing adaptive algorithms in convergence rate and communication efficiency.
Latent FxLMS accelerates ANC by adapting along low-dimensional filter weights.
problem Improving active noise control with neural adaptive filters.
method Training an auto-encoder on filter coefficients, constraining weights to latent variables, and updating in latent space.
result Latent FxLMS converges in fewer steps with comparable error to standard FxLMS.
Paper proposes an adaptive gradient method for federated learning.
problem Communication efficiency in federated learning.
method Adaptive gradient method for federated learning.
result Guaranteed convergence and communication efficiency in federated learning.
Coordinate descent (CD) algorithms have become the method of choice for solving a number of optimization problems in machine learning. They are particularly popular for training linear models, including linear support vector machine classification, LASSO regression, and logistic regression. We consider general CD with …
Contextual policy search allows adapting robotic movement primitives to different situations. For instance, a locomotion primitive might be adapted to different terrain inclinations or desired walking speeds. Such an adaptation is often achievable by modifying a small number of hyperparameters. However, learning, when …
HollowFlow speeds up likelihood evaluation for large-scale models.
problem Prohibitive scaling of sample likelihood computations in flow-based models.
method Introduces HollowFlow, a flow-based generative model using a NoBGNN with a block-diagonal Jacobian structure.
result Achieves up to O(n^2) speed-up in likelihood evaluation for large systems.
We investigate the adaptive robust control framework for portfolio optimization and loss-based hedging under drift and volatility uncertainty. Adaptive robust problems offer many advantages but require handling a double optimization problem (infimum over market measures, supremum over the control) at each instance. Mor…
We explore the competitive effects of reaction time of automated trading strategies in simulated financial markets containing a single exchange with public limit order book and continuous double auction matching. A large body of research conducted over several decades has been devoted to trading agent design and simula…
PCHAL and PCHAR use principal components to speed up HAL and HAR methods.
problem Computational infeasibility in high dimensions for HAL and HAR.
method Outcome-blind principal component reduction of HAL basis.
result Empirical performance comparable to HAL and HAR, with computational gains.