The paper speeds up Gaussian process regression for large datasets.
problem High computational costs in Gaussian process regression for large data sets.
method Derives simple results to speed up GPR learning and model comparison.
result Significant speed-up in Bayesian model comparison and evidence evaluation.
Speeds up training and inference by pruning entire channels before training.
problem Training and inference speed in deep neural networks.
method Structured pruning applied before training, focusing on removing entire channels and hidden units.
result 2x speedup in training and 3x speedup in inference.
Paper speeds up and extends Subclass Discriminant Analysis methods.
problem Improving efficiency and handling multi-view data in Subclass Discriminant Analysis.
method Developed a speed-up approach based on graph embedding and spectral regression, and a novel multi-view solution.
result Proposed methods achieve competitive performance and significantly decrease training time.
Quantum computing speeds up asset pricing models exponentially.
problem Solving dynamic nonlinear asset pricing models efficiently.
method Utilizes quantum superposition and entanglement to solve models exponentially faster than classical methods.
result Exponential computational speed-up for solving asset pricing models.
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.
This paper studies parallelization schemes for stochastic Vector Quantization algorithms in order to obtain time speed-ups using distributed resources. We show that the most intuitive parallelization scheme does not lead to better performances than the sequential algorithm. Another distributed scheme is therefore intro…
Paper analyzes Scaffold algorithm for federated learning, proving linear speed-up with stochastic gradients.
problem Understanding the impact of stochastic gradients on the Scaffold algorithm's performance.
method Proved linear speed-up in the number of clients using a Markov chain analysis of global parameters and control variates.
result Scaffold achieves linear speed-up in the number of clients up to higher-order terms in the step size, but retains a higher-order bias.
This work learns a default policy to speed up RL learning by restricting information it receives.
problem Information asymmetry in reinforcement learning.
method KL regularized expected reward objective with a learned default policy.
result Learning a default policy can significantly speed up and improve RL learning.
Quantum algorithms speed up reinforcement learning policies in large state-action spaces.
problem Limitations of quantum access in training reinforcement learning policies.
method Designing quantum algorithms to train reinforcement learning policies.
result Quantum algorithms offer full quadratic speed-ups in sample complexity for well-behaved policies.
Study improves privacy-preserving online prediction from experts with speed-ups.
problem Privacy-preserving online prediction from experts with speed-ups.
method Differentially private federated online prediction algorithms.
result Achieves m-fold regret speed-up with low-loss expert in federated setting. Quantum computing speeds up Bermudan option pricing.
problem Efficient pricing of financial derivatives, especially Bermudan options.
method Quantum amplitude estimation combined with Chebyshev interpolation.
result Quadratic speed-up over classical methods.
Meta-learning speeds up learning new tasks.
problem Designing and improving machine learning pipelines.
method Observing and learning from different machine learning approaches.
result Learning new tasks much faster than traditional methods.
Exact solver speeds up Weston-Watkins SVM subproblem significantly.
problem Improving performance of Weston-Watkins multiclass SVM.
method Novel reparametrization for exact subproblem solving.
result Significant speed-up over state-of-the-art solvers for large number of classes.
New RL approach speeds up training across tasks.
problem Training reinforcement learning models quickly and efficiently.
method Combines planning quasi-metric and task-specific aimers.
result Achieves multiple-fold speed-up on bit-flip and robotic arm tasks.
New method speeds up nuclear-norm constrained learning over multiple machines.
problem Synchronization slowdown and high communication costs in large-scale learning.
method Asynchronous Stochastic Frank-Wolfe (SFW-asyn) method.
result SFW-asyn achieves the same convergence rate as vanilla SFW but with speed-ups almost linear to the number of machines.
A new algorithm speeds up matrix operations in Neural Networks.
problem Time-consuming matrix operations in Neural Networks.
method An algorithm that increases the degree of parallelism of matrix multiplication.
result The algorithm speeds up several matrix operations in Neural Networks.
Tensor trains speed up option pricing for multi-asset options.
problem Speeding up option pricing for multi-asset options.
method Tensor train learning algorithms to compress functions with parameter dependence.
result The proposed method outperforms Monte Carlo-based pricing in computational complexity.
Accelerates coordinate descent methods for machine learning problems.
problem Slowness of coordinate descent methods in machine learning.
method Extrapolation-based accelerated coordinate descent.
result Significant speed-up in practice compared to existing methods.
This paper speeds up iterative GP inference with warm starting.
problem Improving scalability of Gaussian process inference.
method Warm starting sequential posteriors using known solutions.
result Significant speed-ups and improved Bayesian optimisation performance.
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.
Enhances supervised learning speed with KT algorithm.
problem Speed up supervised learning tasks with minimal loss.
method Generalizes kernel thinning to supervised learning, combining NW and KRR with KT.
result KT-based estimators offer superior computational and statistical efficiency.
FedSARSA converges with heterogeneous agents, achieving linear speed-up.
problem Convergence analysis of Federated SARSA with heterogeneous agents.
method Linear function approximation, local training, multi-step error expansion.
result FedSARSA achieves linear speed-up with respect to the number of agents.
Quantum algorithms for multi-armed bandits are explored with limited reward access.
problem Exploring quantum speed-ups in multi-armed bandit problems with limited reward information.
method Introduced new bandit models and showed query complexity equivalence with classical algorithms.
result No quadratic speed-up is possible for multi-armed bandits with limited reward access.
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.
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.
Quantum SVM clustering speeds up big data analysis.
problem Performance degradation of classical SVM clustering on big data.
method Developed a quantum version of SVM clustering using quantum support vector machine and kernels.
result Significant speed-up gain on run-time complexity.
QWO speeds up causal discovery in LiGAMs by O(n2).
problem Scalability issues in permutation-based causal discovery methods for LiGAMs.
method Constructing a specific DAG for a permutation and searching over permutations to minimize edge count.
result QWO achieves a speed-up of O(n2) compared to state-of-the-art methods. This paper speeds up large-scale deep learning training.
problem Training large-scale deep architectures is slow and resource-intensive.
method Systematic approach to identify bottlenecks, develop guidelines, and derive lemmas.
result Developed procedures and lemmas for setting minibatch size, choosing algorithms, and determining component quantities.
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.
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.
Parallel training speeds up neural network training, but process communication costs limit efficiency.
problem Efficiently training complex neural networks in real-time.
method Implemented Network Parallel Training using Cannon's Algorithm for matrix multiplication.
result Increasing the number of processes speeds up training until communication costs become prohibitive.
This dissertation shows that careful injection of noise into sample data can substantially speed up Expectation-Maximization algorithms. Expectation-Maximization algorithms are a class of iterative algorithms for extracting maximum likelihood estimates from corrupted or incomplete data. The convergence speed-up is an e…
Speeds up complex portfolio exposure calculations.
problem Calculating exposure of portfolios with exotic derivatives.
method Least Squares Monte Carlo (LSMC) technique.
result Significantly reduces computation time for nested Monte Carlo.
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.
WeSpeR speeds up non-linear shrinkage for high-dimensional weighted covariance.
problem Computing non-linear shrinkage formulas for high-dimensional weighted sample covariance.
method Derive extit{WeSpeR} algorithm using asymptotic sample spectrum properties.
result Significantly speeds up non-linear shrinkage in dimensions higher than 1000.
New algorithm speeds up RNN time series prediction by filtering noise.
problem Predicting smooth trajectories from noisy time series data.
method Analyzed RNN dynamics to propose an efficient noise filtering algorithm.
result Significant speedup in predictive process without accuracy loss.
New techniques for faster and more compact speech recognition models.
problem Efficiency and compactness in speech recognition neural networks.
method Trace norm regularization for low rank factoring and ARM optimized kernels for faster inference.
result 3x to 7x speed up in inference on ARM processors compared to gemmlowp.
Noisy EM speeds up convergence in mixture models.
problem Speeding up convergence of EM algorithms in mixture models.
method Noisy Expectation Maximization (NEM) algorithm with various noise injection methods.
result NEM algorithm speeds up convergence to local maxima in mixture models.
A new algorithm speeds up feature selection by 65.77%.
problem Efficiently selecting features in high-dimensional data.
method Dropping Forward-Backward algorithm, reducing rescanning of features.
result Significantly faster than stepwise procedure, maintaining good performance.
Multirate training speeds up neural network fine-tuning.
problem Efficiently fine-tuning deep neural networks.
method Partitioning neural network parameters into fast and slow parts, updating slowly over longer intervals.
result Significant computational speed-up for transfer learning tasks.
Interactive teaching speeds up IRL learning with adaptive demonstrations.
problem Tackles the challenge of accelerating IRL learning with teacher assistance.
method Interactive teaching framework where a teacher adapts demonstrations based on the learner's policy.
result Teaching algorithms converge in the omniscient setting, speeding up learning.
New method speeds up deep neural networks inference.
problem Inference speed of deep neural networks.
method Maximum volume algorithm for reduced-order modeling.
result Convolutional layers can be replaced with smaller fully-connected layers with minimal accuracy loss.
Paper proposes efficient AUC estimation in sliding windows.
problem Efficiently monitoring AUC in large sliding windows over data streams.
method Algorithm groups data points to estimate AUC with O((logk)/ε) time per update. result Achieves significant speed-up over exact computation with modest accuracy loss.
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.
Non-autoregressive model speeds up sequence generation tasks.
problem Efficiency in sequence generation tasks.
method Iterative refinement based on latent variable models and denoising autoencoders.
result Significant speedup in decoding with comparable quality.
This paper explores how random sampling and coding can speed up approximate matrix multiplication.
problem Efficiently computing large-scale matrix multiplications in distributed systems.
method Proposes two schemes: coding for recovery and random sampling for approximation.
result Investigates tradeoffs between recovery threshold and approximation error.
A new method speeds up option valuation computations.
problem Computing option values efficiently with high accuracy.
method Multilevel Monte Carlo method.
result Significant speed-up in computations for higher accuracy.