Optimizes PCB stack-up design for high-speed circuits.
problem Efficiently optimize many parameters in PCB stack-up design.
method Parallel and intelligent Bayesian optimization for stripline design.
result Improves accuracy and efficiency of PCB stack-up optimization.
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.
Quantum computers can speed up machine learning optimization problems.
problem Long computation times and high resource requirements for classical optimization algorithms in machine learning.
method Developed a mathematical model to leverage quantum parallelism for machine learning.
result Quantum machine learning applied to a 3D time-varying image demonstrated significant speedup.
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.
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.
New optimization method speeds up learning from data.
problem Efficiently optimizing large datasets for machine learning.
method Minibatch stochastic variance reduced proximal iterations.
result Improved convergence speed for quadratic objectives.
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.
Optimal execution method uses rough path signatures for approximate solutions.
problem Finding optimal trading speed in financial markets.
method Approximate solutions via signature method for geometric rough paths and continuous price impact.
result Accurate and flexible optimal trading speed solutions for various market conditions.
Swarming improves convergence speed in distributed stochastic optimization.
problem Faster convergence in distributed stochastic optimization.
method Inspired by swarming, each thread performs a stochastic gradient descent algorithm with a swarming potential, achieving better performance than a centralized algorithm.
result The swarming-based approach converges faster than a centralized algorithm, with a monotone decreasing error bound in network size and connectivity.
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.
New algorithm improves stability and speed of adversarial training.
problem Discontinuity in solutions of inner maximization in minimax optimization.
method Epsilon-subgradient descent algorithm with K candidate solutions.
result Significant improvement in stability and convergence speed.
PPOKFAC combines PPO and K-FAC for better sample efficiency and scalability.
problem Improving sample efficiency and scalability of Proximal Policy Optimization.
method Combines PPO objective with K-FAC natural gradient optimization.
result PPOKFAC outperforms PPO in sample complexity and training speed.
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.
Distributed Gradient Descent achieves optimal rates in non-parametric regression with linear speed-up.
problem Optimal statistical rates in decentralized non-parametric regression.
method Distributed Gradient Descent with i.i.d. samples and linear speed-up.
result Achieves optimal statistical rates with linear speed-up in the big data regime.
Novel PairNet speeds up ANN training with fast hyperparameter optimization.
problem Slow training of traditional ANNs with many hyperparameters.
method Partition inputs into subspaces, optimize hyperparameters via linear equations, train local PairNets in subspaces.
result PairNet achieves higher speeds and lower MSEs than traditional ANNs.
New RL algorithm learns optimal policies for MDPs using known structure.
problem Overcoming curse of dimensionality and modeling in MDPs.
method Structure-aware online learning algorithm exploiting known threshold policy.
result Proposed algorithm converges to optimal policy with significant speed improvements.
Optimized HMM using PSO overcomes constraints for better solutions.
problem Finding global optimal solutions for HMM parameters.
method Constrained Particle Swarm Optimization (PSO) to solve HMM parameters, re-normalization and re-mapping to enforce constraints.
result PSOHMM finds better solutions and converges faster than BWHMM.
New method speeds up optimization with non-uniform sampling.
problem Optimizing complex stochastic problems efficiently.
method Stochastic Primal Dual Coordinate Method with Optimality Violation-based Sampling.
result The proposed method and variants outperform other methods in speed.
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.
A new optimization method improves deep learning model training speed.
problem Optimizing large models with natural gradient descent.
method Kronecker-factored eigenbasis for diagonal variance approximation.
result Improves optimization speed for deep network architectures.
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.
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.
New algorithm speeds up LVGGM estimation by solving nonconvex optimization.
problem Estimating the latent variable Gaussian graphical model with sparse and low-rank components.
method Sparsity constrained maximum likelihood estimator with alternating gradient descent and hard thresholding.
result Our algorithm converges linearly to the optimal components up to statistical precision.
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.
Dual SVM training with budget constraint for faster accuracy.
problem Efficient support vector machine training with limited resources.
method Dual subspace ascent algorithm with budget constraint.
result Significant speed-up over primal budget training methods.
GoSGD speeds up deep learning training with gossip exchange.
problem Speeding up the training of deep learning models.
method Distributed optimization using stochastic gradient descent with gossip algorithms.
result GoSGD achieves fully asynchronous and decentralized training.
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.
SVIGL speeds up convergence in stochastic variational inference.
problem Optimizing log-posterior in random field models is difficult.
method Stochastic variational inference with gradient linearization.
result SVIGL improves convergence speed with comparable KL divergence.
Proposes a deep reinforcement learning model for efficient variable speed limits control.
problem Improving traffic flow, safety, and emissions on freeways with varying speed limits.
method Uses a novel actor-critic architecture for deep reinforcement learning to manage dynamic speed limits.
result The proposed method enhances efficiency, safety, and emissions compared to traditional control 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…
Helix speeds up iterative ML development by optimizing workflow execution.
problem Inefficient manual tuning of ML workflows.
method Declarative system that optimizes workflow execution end-to-end and across iterations, minimizing runtime per iteration.
result Up to an order of magnitude reduction in cumulative run time compared to state-of-the-art tools.
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.
New methods speed up Bayesian experimental design.
problem Difficulty in estimating expected information gain.
method Amortized variational inference for fast EIG estimation.
result Significant gains in speed and accuracy.
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.
Improves RL learning speed by leveraging subspace generalization.
problem Slow learning in RL due to limited state-space generalization.
method Model-based RL method using subspaces to enhance learning speed.
result MoBLeS improves learning speed in early trials through subspace generalization.
Poseidon optimizes deep learning training on GPU clusters by reducing network communication.
problem Substantial parameter synchronization over the network in distributed DL implementations.
method Overlap communication and computation, use a hybrid communication scheme.
result Achieves significant speed-ups in DL training on GPU clusters.
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.
Exploring how noise and curvature affect optimization and generalization.
problem The interaction between noise and curvature in optimization and generalization.
method Analyzing the speed of minimizing expected loss with stochastic methods, distinguishing between Fisher, Hessian, and gradient covariance matrices.
result Clarifying the role of curvature and noise in estimating the generalization gap.
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.