arXiv research

Paper analyzes Scaffold algorithm for federated learning, proving linear speed-up with stochastic gradients.

WeSpeR speeds up non-linear shrinkage for high-dimensional weighted covariance.

FedSARSA converges with heterogeneous agents, achieving linear speed-up.

Exact solver speeds up Weston-Watkins SVM subproblem significantly.

This paper speeds up iterative GP inference with warm starting.

K-FAC speeds up training of modern neural networks with linear weight-sharing.

A new algorithm speeds up elliptical slice sampling for truncated multivariate normals.

SCAFFLSA reduces communication complexity for federated learning with heterogeneous clients.

The paper speeds up hyperparameter optimisation in Gaussian processes.

New algorithm speeds up sampling from log-concave distributions over polytopes.

Stochastic variational inference (SVI) employs stochastic optimization to scale up Bayesian computation to massive data. Since SVI is at its core a stochastic gradient-based algorithm, horizontal parallelism can be harnessed to allow larger scale inference. We propose a lock-free parallel implementation for SVI which a…

Orthogonal initialization speeds up convergence in deep linear networks.

LEAD algorithm speeds up decentralized optimization with compression.

We analyse the learning performance of Distributed Gradient Descent in the context of multi-agent decentralised non-parametric regression with the square loss function when i.i.d. samples are assigned to agents. We show that if agents hold sufficiently many samples with respect to the network size, then Distributed Gra…

Statistical image reconstruction (SIR) methods are studied extensively for X-ray computed tomography (CT) due to the potential of acquiring CT scans with reduced X-ray dose while maintaining image quality. However, the longer reconstruction time of SIR methods hinders their use in X-ray CT in practice. To accelerate st…

AdaScale SGD adapts learning rates for large-batch training efficiently.

QWO speeds up causal discovery in LiGAMs by $O(n^2)$.

CodedFedL speeds up federated learning in MEC networks by 15x.

Paper speeds up Gaussian process inference using Matérn kernels.

New initialization methods speed up Sinkhorn algorithm for OT problems.

Coded Federated Learning speeds up training in edge computing networks.

Orthogonal initialization does not speed up training in ultra-wide neural networks.

Warm-start strategies speed up GP inference by 19x.

New method speeds up Gaussian process training and inference for large datasets.

sGBM speeds up gradient boosting by parallelizing and adapting base learners.

Two log-linear approximations speed up optimal transport for deep learning applications.

We propose a method to impose homogeneous linear inequality constraints of the form $Ax\leq 0$ on neural network activations. The proposed method allows a data-driven training approach to be combined with modeling prior knowledge about the task. One way to achieve this task is by means of a projection step at test time…

This paper presents an acceleration framework for packing linear programming problems where the amount of data available is limited, i.e., where the number of constraints m is small compared to the variable dimension n. The framework can be used as a black box to speed up linear programming solvers dramatically, by two…

Novel probabilistic solver speeds up solving related linear systems.

LOT Wassmap speeds up Wasserstein space manifold learning.

Paper presents a faster classical algorithm for principal component regression.

High dimensional regression benefits from sparsity promoting regularizations. Screening rules leverage the known sparsity of the solution by ignoring some variables in the optimization, hence speeding up solvers. When the procedure is proven not to discard features wrongly the rules are said to be \emph{safe}. In this …

Compress++ speeds up distribution compression to near-linear time.

Machine learning speeds up search procedures for sorted tables.

FLOP algorithm speeds up causal structure learning for linear models.

We consider the problem of decomposing a multivariate polynomial as the difference of two convex polynomials. We introduce algebraic techniques which reduce this task to linear, second order cone, and semidefinite programming. This allows us to optimize over subsets of valid difference of convex decompositions (dcds) a…

A new distributed method speeds up sparse model training.

Communication overhead is one of the key challenges that hinders the scalability of distributed optimization algorithms. In this paper, we study local distributed SGD, where data is partitioned among computation nodes, and the computation nodes perform local updates with periodically exchanging the model among the work…

Study iterative regularization for linear models with convex bias, improving robust sparse recovery.

Efficient algorithms speed up adversarial training for linear models.

Quantum algorithm speeds up Gibbs partition function estimation.

Graph neural networks improve solving linear optimization problems.

EiGLasso speeds up sparse Kronecker-sum covariance estimation.

LOT framework speeds up event distance computation in collider physics.

This paper speeds up K-FAC for deep learning by focusing on only a few eigen-modes.

New algorithm speeds up Bayesian UQ for high-dimensional inverse problems.

Many applications that use empirically estimated functions face a curse of dimensionality, because the integrals over most function classes must be approximated by sampling. This paper introduces a novel regression-algorithm that learns linear factored functions (LFF). This class of functions has structural properties …

New algorithm speeds up path computation for optimal models.