Characterizes optimal-speed quantum state evolution Hamiltonians.
problem Optimal-speed unitary time evolution of pure and quasi-pure quantum states.
method Construction of the manifold of pure states and isometry with flag manifold, characterization of equigeodesic vectors.
result Hamiltonians generating optimal-speed time evolution are fully characterized by equigeodesic vectors of the flag manifold.
Diffusion models' speed-accuracy relations derived from thermodynamics.
problem Understanding the trade-off between model speed and accuracy.
method Connecting diffusion models to thermodynamics and optimal transport.
result Speed-accuracy relations derived, providing insights into optimal learning protocols.
Hybrid model improves wind speed prediction accuracy using MLP and WOA.
problem Improving wind speed prediction accuracy for renewable energy control.
method Combining MLP with Whale Optimization Algorithm (WOA) for data preprocessing and model optimization.
result The hybrid MLP-WOA model outperformed standalone MLP model in wind speed prediction accuracy.
Presents SPEED, an algorithm for optimal policy evaluation in linear bandits with heteroscedastic noise.
problem Optimal data collection for policy evaluation in linear bandits with heteroscedastic reward noise.
method Formulated an optimal design for weighted least squares estimates, derived the optimal sample allocation, introduced SPEED algorithm, and derived regret bounds.
result SPEED leads to policy evaluation with MSE comparable to oracle strategy and significantly lower than random policy execution.
Design of printed circuit board (PCB) stack-up requires the consideration of characteristic impedance, insertion loss and crosstalk. As there are many parameters in a PCB stack-up design, the optimization of these parameters needs to be efficient and accurate. A less optimal stack-up would lead to expensive PCB materia…
Paper proposes a pre-conditioning method to speed up gradient descent in multi-agent optimization.
problem Speed up convergence of gradient descent in multi-agent optimization problems.
method Iterative pre-conditioning approach to mitigate the effect of problem conditioning.
result Significant improvement in convergence speed of gradient descent method.
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.
Gradient flow preserves speed for integral Menger curvature curves.
problem Optimizing curves with integral Menger curvature constraints.
method Projected Sobolev gradient flow in Hilbert space.
result Long-time existence and C1,1-bounds for the flow. New limits found for training deep learning models efficiently.
problem Optimizing the training speed of deep learning models without sacrificing accuracy.
method Applied stochastic thermodynamics to set speed limits for neural network training.
result Training neural networks is optimal within certain scaling assumptions.
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.
Modeling vessel speed to balance efficiency and environmental risks in Arctic shipping.
problem Balancing vessel speed with environmental and ecological risks in Arctic shipping.
method Inverse control constrained optimization framework with risk parameters estimated from AIS data.
result Distinct decision-making patterns across vessel types and navigational statuses, with varying sensitivity to ice and whale risks.
Ringleader ASGD optimizes SGD for diverse edge devices with varying data and computation speeds.
problem Scalable distributed optimization with heterogeneous devices and data.
method Ringleader ASGD, an asynchronous SGD algorithm.
result Achieves optimal time complexity under data heterogeneity and arbitrary computation speeds.
A neural network speeds up computation of Wasserstein barycenters by 60x.
problem Computing Wasserstein barycenters is computationally demanding.
method Trained a deep convolutional neural network to compute Wasserstein barycenters.
result Computational times reduced from milliseconds to seconds.
Space mapping speeds up shape optimization for PDEs.
problem Efficiently solving shape optimization problems constrained by PDEs.
method Combines fine and coarse model optimizations using Riemannian metrics.
result Space mapping methods are highly efficient for complex shape optimization problems.
Two algorithms improve K-means clustering speed without sacrificing quality.
problem Improving clustering quality of K-means while speeding up the process.
method Divisive K-means and Parallel Two-Phase K-means.
result Achieved empirically global optimum clustering results with lower complexity.
Classical optimization algorithms in machine learning often take a long time to compute when applied to a multi-dimensional problem and require a huge amount of CPU and GPU resource. Quantum parallelism has a potential to speed up machine learning algorithms. We describe a generic mathematical model to leverage quantum…
FastForest boosts Random Forest speed by 24%.
problem Efficiency in processing speed for Random Forest.
method Subsample Aggregating, Logarithmic Split-Point Sampling, Dynamic Restricted Subspacing.
result Average 24% increase in processing speed with accuracy maintained.
Study of fastest paths in anisotropic media via Finsler geometry.
problem Optimal paths in media with varying speeds and interfaces.
method Finsler geodesics refracted at interfaces, satisfying specific conditions.
result Establishes generalized Snell's and reflection laws.
GOAT improves graph matching speed and accuracy using optimal transport.
problem Efficiently matching large graphs in various applications.
method Replaces linear assignment with optimal transport methods.
result GOAT provides improvements in speed and accuracy.
Quantum computing speeds up neural network training and retraining.
problem Inefficient classical training and retraining of neural networks.
method Adiabatic quantum computing to optimize Kolmogorov-Arnold Networks using Bezier curves.
result Quantum optimization achieves 100x faster retraining compared to classical methods.
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.
We study the optimal execution of market and limit orders with permanent and temporary price impacts as well as uncertainty in the filling of limit orders. Our continuous-time model incorporates a trade speed limiter and a trader director to provide better control on the trading rates. We formulate a stochastic control…
New method speeds up k-means clustering using sketch-and-solve.
problem Efficiently solving k-means clustering for large datasets.
method Sketch-and-solve approach with Peng-Wei semidefinite relaxation.
result Provides high-confidence lower bounds on k-means optimal value.
Warm-start strategies speed up GP inference by 19x.
problem Efficient sequential inference in Gaussian processes.
method Three warm-start strategies exploiting smaller linear systems.
result Warm-starting achieves up to 19x speed-up in convergence.
Optimizes neural networks by removing unnecessary layers, improving performance and speed.
problem Finding the optimal depth of neural networks to improve performance and speed.
method Develops a fast end-to-end method for training lightweight neural networks with multiple classifier heads, allowing the model to determine the importance of each head and choosing a single shallow classifier.
result Significantly reduces the number of parameters and accelerates inference, outperforming many standard pruning methods.
In a recent paper, Alfonsi, Fruth and Schied (AFS) propose a simple order book based model for the impact of large orders on stock prices. They use this model to derive optimal strategies for the execution of large orders. We apply these strategies to an agent-based stochastic order book model that was recently propose…
This work speeds up hyperparameter selection for non-smooth convex models using implicit differentiation.
problem Optimizing hyperparameters of non-smooth convex models.
method Implicit differentiation of proximal gradient and coordinate descent methods.
result Implicit differentiation can speed up hyperparameter optimization, especially for non-smooth problems.
NoTMF forecasts sparse urban road movement speeds with nonstationary temporal matrix factorization.
problem Sparse and nonstationary movement speed data from urban roads.
method Nonstationary Temporal Matrix Factorization (NoTMF) model.
result NoTMF outperforms baseline models in forecasting urban road movement speeds.
This paper speeds up OCSSVM training using SMO.
problem Training One-Class Slab SVMs is slow.
method Uses updated SMO to divide large problems into smaller, analytically solvable subproblems.
result Training OCSSVMs scales better with large datasets.
Multithreshold Entropy Linear Classifier (MELC) is a density based model which searches for a linear projection maximizing the Cauchy-Schwarz Divergence of dataset kernel density estimation. Despite its good empirical results, one of its drawbacks is the optimization speed. In this paper we analyze how one can speed it…
New methods solve graph sparsity optimization problems faster.
problem Complex graph sparsity optimization problems in disease outbreak monitoring and social network analysis.
method Stochastic variance-reduced gradient-based methods GraphSVRG-IHT and GraphSCSG-IHT.
result Our methods achieve linear convergence speed.
AcceleratedLiNGAM speeds up causal discovery methods for large datasets.
problem Slow causal discovery methods for large-scale datasets.
method Parallelized LiNGAM method with GPU acceleration.
result Up to 32-fold speed-up on benchmark datasets.
The ever increasing computational cost of Deep Neural Networks (DNN) and the demand for energy efficient hardware for DNN acceleration has made accuracy and hardware cost co-optimization for DNNs tremendously important, especially for edge devices. Owing to the large parameter space and cost of evaluating each paramete…
LEAD algorithm speeds up decentralized optimization with compression.
problem Slow convergence and stability issues in decentralized optimization with compression.
method Proposes the first linearly convergent decentralized algorithm with compression.
result First consensus error bound for coupled dynamics of primal and dual updates.
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.
Traditionally, an artificial neural network (ANN) is trained slowly by a gradient descent algorithm such as the backpropagation algorithm since a large number of hyperparameters of the ANN need to be fine-tuned with many training epochs. To highly speed up training, we created a novel shallow 4-layer ANN called "Pairwi…
The speed at which one can minimize an expected loss using stochastic methods depends on two properties: the curvature of the loss and the variance of the gradients. While most previous works focus on one or the other of these properties, we explore how their interaction affects optimization speed. Further, as the ulti…
We present a method for obtaining approximate solutions to the problem of optimal execution, based on a signature method. The framework is general, only requiring that the price process is a geometric rough path and the price impact function is a continuous function of the trading speed. Following an approximation of t…
In this technical report, we consider an approach that combines the PPO objective and K-FAC natural gradient optimization, for which we call PPOKFAC. We perform a range of empirical analysis on various aspects of the algorithm, such as sample complexity, training speed, and sensitivity to batch size and training epochs…
New initialization methods speed up Sinkhorn algorithm for OT problems.
problem Improving runtime of the Sinkhorn algorithm for optimal transport problems.
method Data-dependent initializers for Sinkhorn algorithm, based on closed-form solutions for specific settings.
result Data-dependent initializers result in dramatic speed-ups without affecting differentiability.
A deep learning model speeds up computation of numerous implied volatilities.
problem Frequent computation of numerous implied volatilities using iteration methods like Newton-Raphson reaches processing speed limits.
method Emulated Newton-Raphson method using PyTorch and optimized with TensorRT.
result Up to 1,000 times faster than a benchmark implementation of Newton-Raphson.
New algorithm speeds up path computation for optimal models.
problem Finding the exact path of optimal models from a finite set.
method Dynamic programming approach for linear time computation.
result Dynamic programming achieves linear time for breakpoints computation.
To overcome the curse of dimensionality and curse of modeling in Dynamic Programming (DP) methods for solving classical Markov Decision Process (MDP) problems, Reinforcement Learning (RL) algorithms are popular. In this paper, we consider an infinite-horizon average reward MDP problem and prove the optimality of the th…
A new screening rule 'dynamic Sasvi' improves sparse optimization speed.
problem Sparse optimization problem identification.
method Flexible framework based on Fenchel-Rockafellar duality for norm-regularized least squares.
result Dynamic Sasvi can eliminate more features and increase solver speed.
Sparse perturbations improve convergence in SZO methods for faster training.
problem Dependency of SZO methods on function dimensionality limits their convergence speed.
method Sparse perturbations reduce the effective dimensionality of the optimization problem.
result Sparse SZO optimization leads to faster convergence in training loss and test accuracy.
Deep neural networks have gained tremendous popularity in last few years. They have been applied for the task of classification in almost every domain. Despite the success, deep networks can be incredibly slow to train for even moderate sized models on sufficiently large datasets. Additionally, these networks require l…
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.
A new principle for optimizer selection improves training speed and performance.
problem Finding the best optimizer hyperparameters for faster training.
method Formulate optimizer selection as maximizing the expected drop rate in loss, treating gradients and updates as signals and an optimizer as a causal filter.
result Greedy optimizer selection yields stable and effective momentum rules.