New algorithms estimate matrix norms without matrix multiplication.
problem Estimating matrix norms efficiently in a matrix-free setting.
method Randomized algorithms based on Hutchinson's estimator modifications.
result Oracle complexity bounds for two-to-infinity and one-to-two norms.
This paper proposes a novel profile likelihood method for estimating the covariance parameters in exploratory factor analysis of high-dimensional Gaussian datasets with fewer observations than number of variables. An implicitly restarted Lanczos algorithm and a limited-memory quasi-Newton method are implemented to deve…
Large-scale generalized linear array models (GLAMs) can be challenging to fit. Computation and storage of its tensor product design matrix can be impossible due to time and memory constraints, and previously considered design matrix free algorithms do not scale well with the dimension of the parameter vector. A new des…
New preconditioners speed up SGD on Lie groups.
problem Accelerating SGD convergence on Lie groups.
method Online updating of low-rank and matrix-free preconditioners.
result Preconditioners maintain symmetry and invariance.
LASER compresses recursive model activations by exploiting their low-dimensional structure.
problem Understanding and optimizing the geometric structure of recursive reasoning trajectories.
method Dynamic low-rank basis tracking via matrix-free subspace tracking with a fidelity-triggered reset mechanism.
result Recursive activations occupy a linear, low-dimensional subspace that can be compressed efficiently.
Unified methods for fast column selection in various applications.
problem Efficiently selecting columns for low-rank approximations in data science and machine learning.
method Deterministic and randomized algorithms exploiting nuclear scores.
result Theoretical guarantees and performance bounds for column selection.
HD algorithm simulates dynamics on random matrix ensembles without generating full matrices.
problem Simulating dynamics on dense random matrix ensembles with high space and time complexity.
method Householder reflectors for adaptive and recursive construction, deferring decisions.
result Significant reductions in runtime and memory footprint for practical T≪n. We provide an online convex optimization algorithm with regret that interpolates between the regret of an algorithm using an optimal preconditioning matrix and one using a diagonal preconditioning matrix. Our regret bound is never worse than that obtained by diagonal preconditioning, and in certain setting even surpass…
We study the task of semi-supervised learning on multilayer graphs by taking into account both labeled and unlabeled observations together with the information encoded by each individual graph layer. We propose a regularizer based on the generalized matrix mean, which is a one-parameter family of matrix means that incl…
New method computes affine normal directions efficiently for sparse polynomials.
problem Computing affine normal directions is computationally expensive in high dimensions.
method Reduces third-order tensor contraction to matrix-free formulation using log-determinant gradient.
result Scalable implementations with near-linear scaling in dimension and sparsity.
In this paper, we present a scalable distributed implementation of the Sampled Limited-memory Symmetric Rank-1 (S-LSR1) algorithm. First, we show that a naive distributed implementation of S-LSR1 requires multiple rounds of expensive communications at every iteration and thus is inefficient. We then propose DS-LSR1, a …
In general, adversarial perturbations superimposed on inputs are realistic threats for a deep neural network (DNN). In this paper, we propose a practical generation method of such adversarial perturbation to be applied to black-box attacks that demand access to an input-output relationship only. Thus, the attackers gen…
New method improves Kalman filtering and smoothing for large state spaces.
problem High computational cost and uncertainty in large-scale Kalman filtering.
method Probabilistic numerical method leveraging GPU acceleration and tunable trade-off.
result Mitigates scaling issues and provides more accurate uncertainty estimates.
A new iterative K-FAC algorithm reduces training time and memory usage.
problem Training deep learning models efficiently.
method Uses conjugate gradient to approximate Fisher information matrix without generating the matrix or factors.
result Time and memory complexity of iterative CG-FAC is less than standard K-FAC.
Bayesian deep learning avoids underfitting by projecting onto null space of generalized Gauss-Newton matrix.
problem Bayesian deep learning often underfits, leading to less accurate predictions than point estimates.
method Proposes a matrix-free algorithm to project onto the null space of the generalized Gauss-Newton matrix, ensuring Bayesian predictions do not underfit.
result The method scales to large models, including vision transformers with 28 million parameters, and avoids underfitting.
Boosts linear neurons for faster convergence in neural networks.
problem Optimizing neural networks' neurons in function space.
method Reparameterizing network to whiten neuron features using Boosted Backpropagation.
result Equivalent to preconditioned gradient descent, leading to faster convergence.
Developing stable and scalable probabilistic ODE solvers for stiff and high-dimensional problems.
problem Stiff and high-dimensional ODEs
method Matrix-free update step and iterative re-linearization
result Improved stability and scalability
Graph networks struggle with multi-task learning due to varying property loss surface curvatures.
problem Graph networks underperform in multi-task learning for crystal and molecule properties.
method Assessed curvature of property loss surfaces via spectral properties of Hessians, matrix-free using randomized numerical linear algebra.
result Varying curvature of property loss surfaces explains graph networks' multi-task learning inefficiency.
A hybrid method clusters and characterizes cancer data efficiently.
problem Challenges in clustering high-dimensional biomedical data.
method Gaussian mixture with generalized factor analyzers for efficient estimation.
result Our approach outperforms existing methods with faster convergence and higher accuracy.
Study limits of circadian synchronization under different light signals.
problem Disruption of circadian rhythms due to misalignment with external light signals.
method Matrix-free approach for locating periodic steady states, numerical continuation, bifurcation diagrams, unsupervised learning.
result Limits of circadian synchronization to external light signals of different frequency and duty cycle.
New method solves optimization problems faster than existing methods.
problem Large-scale nonconvex optimization problems.
method ARC method using LQN matrices with exact CR subproblem solution.
result Exact solutions to CR subproblem found in matrix-free manner.
New method for online inference of constrained optimization problems.
problem Online inference of constrained stochastic optimization problems.
method Random scaling of Sketched Stochastic Sequential Quadratic Programming (SSQP).
result Asymptotically valid confidence intervals and matrix-free computation.
We propose a method to assign non-unitary TQFTs to certain SCFTs, deriving bounds and examples.
problem Assigning non-unitary TQFTs to specific SCFTs of rank 0.
method Using degenerate limits of SCFTs, extracting modular data from supersymmetric partition functions, and proposing a dictionary.
result Deriving a lower bound on the free energy of SCFTs and showing it is saturated by a specific SCFT.
Framework learns inter-electronic potential for molecular dynamics.
problem Predicting time-dependent Hartree-Fock dynamics from electron density.
method Developed three models using four-index tensors, preserving symmetries.
result Model with eight-fold symmetry performs best across metrics.
Our work connects parameter magnitudes and Hessian eigenspaces in deep neural nets.
problem Understanding the relationship between parameter magnitudes and Hessian curvature in deep learning models.
method Developed a matrix-free algorithm based on sketched SVDs to measure similarity between parameter masks and Hessian eigenspaces.
result Top Hessian eigenvectors tend to be concentrated around larger parameters, indicating a connection between parameter magnitudes and loss curvature.