New convergence rates for shuffling gradient methods without strong convexity.
problem Theoretical gap between shuffling gradient methods' empirical success and established convergence rates.
method Proved last-iterate convergence rates for shuffling gradient methods using function value gap.
result First last-iterate convergence rates for shuffling gradient methods without strong convexity.
Improved iterative methods for risk parity portfolio weights.
problem Solving for portfolio weights in risk parity allocation.
method Enhanced CCD and Newton methods, including a rescaling step and improved initial guess.
result Improved CCD method is the best, three times faster with 40% fewer iterations.
Iterative method learns unknown constraints for MPC control.
problem Learning to satisfy unknown polyhedral state constraints in iterative MPC.
method Collects and improves estimates of unknown constraints using collected data, designs an MPC controller to satisfy the estimated constraints.
result Robust and probabilistic guarantees of constraint satisfaction as a function of task iterations.
New iterative method solves Yamabe problem on small domains.
problem Solving Yamabe equation on small Riemannian domains.
method Iterative scheme to solve Yamabe equation without functional minimization.
result Solves Yamabe equation on small domains with constant scalar curvature.
We propose a new method for robust PCA -- the task of recovering a low-rank matrix from sparse corruptions that are of unknown value and support. Our method involves alternating between projecting appropriate residuals onto the set of low-rank matrices, and the set of sparse matrices; each projection is {\em non-convex…
Improved matching for multiple objects using a novel reweighting method.
problem Current multi-object matching methods have limitations and are not robust.
method Proposes a novel iterative reweighting strategy using the graph connection Laplacian.
result Demonstrates superior performance over state-of-the-art methods.
A new method for fast, non-iterative graphical model estimation.
problem Scalability issues in iterative proportional fitting for high-dimensional data.
method Non-iterative approach for positive definite graphical model estimation.
result The proposed method outperforms state-of-the-art methods in high-dimensional settings.
Iterative method 'Concent' corrects spectrum bias in covariance matrices.
problem Consistent bias in the spectrum of covariance matrices.
method 'Concent' iterative algorithm.
result Corrects spectrum bias for small and moderate dimensions.
Value iteration is a fixed point iteration technique utilized to obtain the optimal value function and policy in a discounted reward Markov Decision Process (MDP). Here, a contraction operator is constructed and applied repeatedly to arrive at the optimal solution. Value iteration is a first order method and therefore …
New method speeds up distributed linear regression.
problem Efficiently solve distributed linear regression problems.
method Iteratively Pre-conditioned Stochastic Gradient Descent (IPSG)
result Converges linearly in expectation to the solution.
LocalKMeans parallelizes Lloyd's algorithm for distributed data.
problem Efficiently clustering data across multiple machines.
method Parallel local iterations with synchronization every L steps.
result Higher required signal-to-noise ratio due to local steps.
New method for curve comparison using iterated integrals and moving frames.
problem Comparing curves robustly to noise and transformations.
method Moving frame method paired with log-signature transform.
result Algorithmic construction of invariants for curve equivalence under rigid motions.
Method teaches students without teachers, estimating true labels from crowdsourcing.
problem Teaching without access to true labels.
method Apply crowdsourcing techniques to estimate true labels and student models for iterative teaching.
result Teaching performance is particularly effective for low-level students.
Improved SEG method converges to Nash equilibrium in bilinear games.
problem Stochastic bilinear minimax optimization problem
method Stochastic ExtraGradient (SEG) method with constant step size, iteration averaging, and scheduled restarting.
result Provable convergence to Nash equilibrium under standard settings, optimal convergence rate in interpolation setting.
New iterative methods improve scalability of Gaussian process approximations for large data.
problem Scalability issues in Gaussian process approximations for large spatial data.
method Iterative methods combined with preconditioners to reduce computational costs.
result Preconditioners accelerate convergence and improve predictive variances.
In this paper we consider l0 regularized convex cone programming problems. In particular, we first propose an iterative hard thresholding (IHT) method and its variant for solving l0 regularized box constrained convex programming. We show that the sequence generated by these methods converges to a local minimizer.…
Due to the surprisingly good representation power of complex distributions, neural network (NN) classifiers are widely used in many tasks which include natural language processing, computer vision and cyber security. In recent works, people noticed the existence of adversarial examples. These adversarial examples break…
This dissertation advances scalable Gaussian processes using iterative methods and pathwise conditioning.
problem The classical Gaussian process formulation is not scalable for large datasets and modern hardware.
method Combining iterative methods and pathwise conditioning to improve scalability.
result Significantly reduced memory requirements and facilitated application to larger datasets.
The big data trend has inspired feature-driven learning tasks, which cannot be handled by conventional machine learning models. Unstructured data produces very large binary matrices with millions of columns when converted to vector form. However, such data is often sparse, and hence can be manageable through the use of…
We propose and analyze a new parallel coordinate descent method---`NSync---in which at each iteration a random subset of coordinates is updated, in parallel, allowing for the subsets to be chosen non-uniformly. We derive convergence rates under a strong convexity assumption, and comment on how to assign probabilities t…
Policy gradient methods with aggregated states can achieve better performance than approximate policy iteration.
problem Approximation errors in policy and value function approximations.
method State-aggregated representations and policy gradient methods.
result Policy gradient methods can achieve a per-period regret bounded by ε, while approximate policy iteration and value iteration have a higher regret.
We propose a novel method for maximum likelihood-based parameter inference in nonlinear and/or non-Gaussian state space models. The method is an iterative procedure with three steps. At each iteration a particle filter is used to estimate the value of the log-likelihood function at the current parameter iterate. Using …
Combines deep learning and iterative methods for robust phase retrieval.
problem Recovering signals from noisy Fourier intensities.
method Regularization-by-denoising combining iterative phase retrieval and deep learning.
result Outperforms other noise-robust phase retrieval algorithms.
We propose and analyze a new type of stochastic first order method: gradient descent with compressed iterates (GDCI). GDCI in each iteration first compresses the current iterate using a lossy randomized compression technique, and subsequently takes a gradient step. This method is a distillation of a key ingredient in t…
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.
New method solves constrained stochastic optimization problems efficiently.
problem Online statistical inference of constrained stochastic nonlinear optimization problems.
method Stochastic Sequential Quadratic Programming (StoSQP) with iterative sketching solver.
result The rescaled primal-dual sequence converges to a mean-zero Gaussian distribution.
A new method solves optimization problems on the generalized Stiefel manifold using random estimates of B.
problem Optimization over the generalized Stiefel manifold in applications like CCA, ICA, and GEVP.
method Cheap stochastic iterative method that converges to critical points on the manifold.
result The method achieves the same convergence rates as Riemannian optimization but with lower per-iteration cost.
New study shows faster convergence of SGD and Kaczmarz methods.
problem Improving convergence rates of iterative linear system solvers.
method Last-iterate convergence analysis of SGD with greedy step size over smooth quadratics.
result The t-th iterate attains an O(1/t3/4) convergence rate. New recommendations improve Gaussian process accuracy and stability.
problem Numerical instabilities and poor test likelihoods in iterative Gaussian process learning.
method Investigated CG tolerance, preconditioner rank, and Lanczos decomposition rank. Recommended small CG tolerance and large root decomposition size.
result L-BFGS-B optimizer achieves convergence with fewer gradient updates, improving Gaussian process accuracy.
In this paper we present a convergence rate analysis of inexact variants of several randomized iterative methods. Among the methods studied are: stochastic gradient descent, stochastic Newton, stochastic proximal point and stochastic subspace ascent. A common feature of these methods is that in their update rule a cert…
A new method speeds up option pricing under Heston's stochastic volatility model.
problem Speeding up option pricing under the Heston model.
method Iterative splitting method applied to a two-dimensional PDE.
result The iterative splitting method provides more accurate option prices and Greeks compared to traditional methods.
We present the use of the fitted Q iteration in algorithmic trading. We show that the fitted Q iteration helps alleviate the dimension problem that the basic Q-learning algorithm faces in application to trading. Furthermore, we introduce a procedure including model fitting and data simulation to enrich training data as…
A new method extracts features from time series data using iterated sums and improves classification accuracy.
problem Time series classification challenges.
method Feature extraction using iterated-sums signature (ISS) followed by a linear classifier.
result Competitive with state-of-the-art methods on UCR archive.
Alternating direction method of multiplier (ADMM) is a popular method used to design distributed versions of a machine learning algorithm, whereby local computations are performed on local data with the output exchanged among neighbors in an iterative fashion. During this iterative process the leakage of data privacy a…
Sharp analysis of power iteration for tensor PCA, improving convergence and stopping criteria.
problem Analyzing the power iteration algorithm for tensor PCA to improve convergence and stopping criteria.
method Sharp bounds on the number of iterations, revealing a smaller algorithmic threshold, proposing a stopping criterion.
result Sharp bounds on the number of iterations required for power method to converge, revealing a smaller algorithmic threshold than previously conjectured.
New ODE models show saddle-point optimization methods converge differently, with last-iterate convergence for OGDA.
problem Analyzing convergence properties of saddle-point optimization methods.
method High-Resolution Differential Equations (HRDEs) to design differential equation models for saddle-point optimization methods.
result HRDEs reveal last-iterate convergence for Optimistic Gradient Descent Ascent (OGDA) in bilinear games.
Paper proves convergence of Markovian iteration for FBSDEs with fully coupled drift and Z process.
problem Proving convergence of Markovian iteration for FBSDEs with fully coupled drift and Z process.
method Differentiation-based approach to handle Z process, uniformly controlling Lipschitz continuity of decoupling fields.
result Proves convergence of Markovian iteration method for FBSDEs with fully coupled drift and Z process.
Paper refutes conjecture on tensor power iteration convergence in overcomplete models.
problem Understanding convergence of tensor power iteration in overcomplete random tensors.
method Analysis of tensor power iteration dynamics from random initialization.
result Polynomially many steps are necessary for convergence, refutes logarithmic conjecture.
A method for estimating parameters from entangled single-sample distributions, robust to high-noise data.
problem Estimating common parameters from entangled single-sample distributions.
method Iterative trimming of samples to estimate the parameter.
result The method can tolerate a constant fraction of high-noise data points.
Improved convergence of fixed-point methods using windowed Anderson acceleration.
problem Improving convergence of fixed-point methods for symmetric operators.
method Windowed Anderson acceleration for symmetric fixed-point iterations.
result Windowed Anderson acceleration improves convergence over standard fixed-point methods.
Researchers compare different gradient methods for ridge regression, finding conjugate gradients have similar performance.
problem Comparing statistical properties of different gradient methods in ridge regression.
method Explicit non-standard error decomposition to bound prediction error of conjugate gradient iterates.
result Conjugate gradient iterates share optimality properties with gradient flow and ridge regression up to a constant factor.
Local Linear embedding (LLE) is a popular dimension reduction method. In this paper, we first show LLE with nonnegative constraint is equivalent to the widely used Laplacian embedding. We further propose to iterate the two steps in LLE repeatedly to improve the results. Thirdly, we relax the kNN constraint of LLE and p…
Adversarial examples have become one of the largest challenges that machine learning models, especially neural network classifiers, face. These adversarial examples break the assumption of attack-free scenario and fool state-of-the-art (SOTA) classifiers with insignificant perturbations to human. So far, researchers ac…
New method learns collective variables using autoencoders for molecular simulations.
problem Learning low-dimensional slow degrees of freedom (collective variables) for molecular simulations.
method Iterative method involving CV learning with autoencoders and reweighting scheme.
result Achieves convergence of learned collective variables.
IRKSN algorithm achieves sparse recovery with wider applicability conditions.
problem Sparse recovery challenges due to NP-hard nature and restrictive conditions.
method IRKSN algorithm based on k-support norm regularizer. result Achieves sparse recovery with explicit constants and standard linear rate.
Principal component analysis (PCA) is one of the most powerful tools in machine learning. The simplest method for PCA, the power iteration, requires O(1/Δ) full-data passes to recover the principal component of a matrix with eigen-gap Δ. Lanczos, a significantly more complex method, achieves an accelerated…
The Ricci iteration is a discrete analogue of the Ricci flow. According to Perelman, the Ricci flow converges to a Kahler-Einstein metric whenever one exists, and it has been conjectured that the Ricci iteration should behave similarly. This article confirms this conjecture. As a special case, this gives a new method o…
Developed an efficient iterative algorithm for SVI model.
problem SVI model's optimizer's strong dependence on input starting point.
method Fixed-point and least-square optimizer.
result Convergence results for fixed-point iterative algorithm in certain situations.