Gradient EM converges globally for over-parameterized Gaussian mixtures.
problem Global convergence of gradient EM for Gaussian mixtures with more than 2 components.
method Likelihood-based convergence analysis framework.
result Gradient EM converges globally with a sublinear rate of O(1/√t).
Extends tracking guarantees for time-varying variational inequalities.
problem Tracking solutions of time-varying variational inequalities.
method Extends existing results to sublinear solution paths and periodic problems.
result Discrete dynamical systems of periodic time-varying VI can exhibit chaotic behavior or converge to the solution.
Paper generalizes extragradient methods for solving equations and inclusions with improved convergence rates.
problem Solving equations and inclusions using extragradient methods.
method Unified and generalized extragradient methods for a broader class of algorithms, analyzing sublinear convergence rates.
result Unified and improved convergence results for various extragradient variants.
A new method solves convex optimization problems on manifolds efficiently.
problem Optimization on Hadamard manifolds with convex objectives.
method Intrinsic Riemannian proximal gradient method.
result Sublinear and linear convergence rates for convex and strongly convex problems, respectively.
The alternating gradient descent (AGD) is a simple but popular algorithm which has been applied to problems in optimization, machine learning, data ming, and signal processing, etc. The algorithm updates two blocks of variables in an alternating manner, in which a gradient step is taken on one block, while keeping the …
New algorithms tackle machine learning problems using manifold proximal point methods.
problem Maximizing the ℓ1 norm of a linear map over the sphere in machine learning.
method Manifold Proximal Point Algorithms (ManPPA) and Stochastic ManPPA (StManPPA).
result ManPPA and StManPPA achieve faster convergence rates than existing methods.
Single-timescale actor-critic finds globally optimal policy.
problem Finding globally optimal policy in reinforcement learning.
method Simultaneous actor and critic updates with linear or deep neural network approximations.
result Actor sequence converges to globally optimal policy at O(K−1/2) rate. New convergence rates found for PnP methods using MMSE denoisers.
problem Asymptotic convergence of PnP methods with MMSE denoisers.
method Explicitly represented MMSE denoiser as an upper Moreau envelope, derived sublinear convergence rates.
result First sublinear convergence guarantee for PnP proximal gradient descent with MMSE denoiser.
Random extrapolation speeds up coordinate descent for sparse and dense data.
problem Efficiently solving primal-dual coordinate descent for sparse and dense data.
method Adapts to sparsity and uses large step sizes for dense data, proving linear convergence under metric subregularity.
result Linear convergence under metric subregularity and optimal sublinear convergence rates in general convex-concave problems.
This paper studies convergence of horospheres in CAT(0) spaces.
problem Analysis of convergence of horospheres in CAT(0) spaces.
method Examines horofunctions associated with sublinearly contracting geodesic rays.
result Horospheres associated with sublinearly contracting horofunctions are convergent.
In [19], a general, inexact, efficient proximal quasi-Newton algorithm for composite optimization problems has been proposed and a sublinear global convergence rate has been established. In this paper, we analyze the convergence properties of this method, both in the exact and inexact setting, in the case when the obje…
Stochastic algorithm achieves sublinear convergence for bi-objective optimization.
problem Optimizing two conflicting functions using gradient or subgradient descent.
method Stochastic alternating algorithm with varying steps for each objective.
result Achieves sublinear convergence rate of O(1/T) under strong convexity.
Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in practice. Motivated by this, we establish a new setup, called Continuous Online Learning (COL), where the gradient of online loss function cha…
PPO algorithm converges to global optimality in multi-agent reinforcement learning.
problem Designing statistical guarantees for policy optimization methods in multi-agent reinforcement learning.
method Leveraging a multi-agent performance difference lemma, a localized action value function is used as a descent direction for each local policy, leading to a multi-agent PPO algorithm.
result The multi-agent PPO algorithm converges to the globally optimal policy at a sublinear rate under standard regularity conditions.
New algorithm achieves sublinear regret in CMDPs without error cancellations.
problem Safety constraints in reinforcement learning with error cancellations.
method Model-based primal-dual algorithm for CMDPs with multiple constraints.
result Achieves sublinear regret without error cancellations.
The paper analyzes sampling efficiency of discrete diffusion models, providing sharp and adaptive guarantees.
problem Theoretical foundations of discrete diffusion models, especially sampling efficiency.
method Continuous-time Markov chain (CTMC) formulation, τ-leaping-based samplers, effective total correlation. result The τ-leaping algorithm achieves an iteration complexity of order ildeO(d/ε) for uniform discrete diffusion, improving existing bounds by a factor of d. Algorithm minimizes regret and converges to equilibria in Markov games.
problem Regret minimization and convergence to equilibria in general-sum Markov games under adversarial opponents.
method Decentralized algorithm that uses policy optimization and controls path length to achieve sublinear regret.
result Sublinear regret guarantees for convergence to correlated equilibrium in Markov games.
The three operator splitting scheme was recently proposed by [Davis and Yin, 2015] as a method to optimize composite objective functions with one convex smooth term and two convex (possibly non-smooth) terms for which we have access to their proximity operator. In this short note we provide an alternative proof for the…
LIBO optimizes repeated bandit tasks without prior knowledge or regret.
problem Optimizing repeated bandit tasks without prior knowledge or regret.
method LIBO sequentially meta-learns a kernel to adapt to the environment and solve tasks with the latest estimate.
result LIBO achieves sublinear lifelong regret, converging to oracle performance as more tasks are solved.
Survey on extragradient methods for solving nonlinear equations and inclusions.
problem Approximating solutions of nonlinear equations and inclusions.
method Unified convergence analysis of extragradient and its variants.
result Sublinear convergence rates for different classes of algorithms.
The paper shows how sublinear biLipschitz equivalences affect Morse boundaries of metric spaces.
problem Understanding how sublinear biLipschitz equivalences affect Morse boundaries of metric spaces.
method Defining sublinear biLipschitz equivalence and Morse boundaries, proving invariance under SBEs, using sublinear rays.
result κ-Morse boundaries of proper geodesic metric spaces are invariant under suitable sublinear biLipschitz equivalences.
Federated learning algorithm improves with intermittent client availability.
problem Performance degradation in Federated Averaging due to client availability changes.
method Federated Latest Averaging (FedLaAvg) uses latest gradients from all clients, even when unavailable.
result FedLaAvg achieves sublinear speedup compared to classical Federated Averaging.
Algorithm maximizes revenue-risk by estimating price impact kernel and optimizing control problems.
problem Maximizing revenue-risk in a risky asset liquidation with unknown price impact.
method Alternates exploration and exploitation phases, uses novel kernel estimation and stability results.
result Sublinear regret achieved with high probability.
In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses. We provide a sublinear convergence rate (to stationary points) for general noncon…
Improved convergence analysis for decentralized non-convex optimization.
problem Minimizing a sum of smooth non-convex functions over a network.
method Gradient tracking in decentralized stochastic gradient descent (GT-DSGD).
result GT-DSGD achieves network-independent performances matching centralized SGD under certain conditions.
We show that Newton's method converges globally at a linear rate for objective functions whose Hessians are stable. This class of problems includes many functions which are not strongly convex, such as logistic regression. Our linear convergence result is (i) affine-invariant, and holds even if an (ii) approximate Hess…
Novel coordinate descent (CD) methods are proposed for minimizing nonconvex functions consisting of three terms: (i) a continuously differentiable term, (ii) a simple convex term, and (iii) a concave and continuous term. First, by extending randomized CD to nonsmooth nonconvex settings, we develop a coordinate subgradi…
The paper improves convergence for linear systems using entropic mirror descent with Polyak stepsizes.
problem Convergence analysis for linear systems with unbounded domain.
method Entropic mirror descent with Polyak stepsizes, sublinear and linear convergence results.
result Generalized convergence result for arbitrary convex functions.
Two of the most fundamental prototypes of greedy optimization are the matching pursuit and Frank-Wolfe algorithms. In this paper, we take a unified view on both classes of methods, leading to the first explicit convergence rates of matching pursuit methods in an optimization sense, for general sets of atoms. We derive …
Method completes mixed matrix from complex surveys with heterogeneous missingness.
problem Recovering a mixed dataframe matrix from complex survey sampling with different missingness patterns.
method Two-stage procedure: logistic regression for missingness modeling, and weighted log-likelihood maximization with low-rank constraint.
result The proposed method achieves sublinear convergence and shows superior performance compared to existing methods.
This work creates a CS for non-negative heavy-tailed data with bounded mean.
problem Constructing a confidence sequence for non-negative heavy-tailed data with bounded mean.
method Non-parametric, non-asymptotic lower confidence sequence construction.
result The constructed CS is efficient and can be converted into a closed-interval CS.
Sublinear LSVI via LSH reduces runtime to sublinear in actions.
problem Efficiently estimating value functions in reinforcement learning with sublinear runtime.
method Formulated as approximate maximum inner product search, used LSH to solve with sublinear time complexity.
result Sublinear runtime while maintaining LSVI's regret.
We discuss a variant of Thompson sampling for nonparametric reinforcement learning in a countable classes of general stochastic environments. These environments can be non-Markov, non-ergodic, and partially observable. We show that Thompson sampling learns the environment class in the sense that (1) asymptotically its …
The aim of this paper is to introduce the sublinear Higson corona and show that the sublinear Higson corona of Euclidean cone of P and X is decomposed into the product of P and that of X. Here P is a compact metric space and X is unbounded proper metric space. For example, the sublinear Higson corona of n-dimensional E…
Stochastic (sub)gradient methods require step size schedule tuning to perform well in practice. Classical tuning strategies decay the step size polynomially and lead to optimal sublinear rates on (strongly) convex problems. An alternative schedule, popular in nonconvex optimization, is called \emph{geometric step decay…
Symmetric nonnegative matrix factorization (SymNMF) has important applications in data analytics problems such as document clustering, community detection and image segmentation. In this paper, we propose a novel nonconvex variable splitting method for solving SymNMF. The proposed algorithm is guaranteed to converge to…
GAIL with neural networks converges to global optima and has a known rate.
problem Uncertainty about GAIL with neural networks achieving global optimality.
method Gradient-based alternating updates algorithm.
result Established sublinear convergence to globally optimal solution.
Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to nonconvexity and even divergence in optimization. As a result, the global convergence …
Study tackles nonlinear factor models with unknown monotone links from incomplete and noisy data.
problem Learning nonlinear factor models with unknown monotone links from incomplete and noisy data.
method Formulated as joint recovery of low-rank factors, loadings, and nonlinear link function; proposed BCD algorithm with regularization.
result Established convergence guarantees and sublinear regret bounds for link-function updates.
New model for Knightian uncertainty with jumps.
problem Knightian uncertainty and non-linear jumps.
method Probabilistic construction of non-linear affine processes with jumps.
result Tractable model for Knightian uncertainty with sublinear expectations.
We give a proof of the sublinear tracking property for sample paths of random walks on various groups acting on spaces with hyperbolic-like properties. As an application, we prove sublinear tracking in Teichmueller distance for random walks on mapping class groups, and on Cayley graphs of a large class of finitely gene…
New methods optimize functions faster with less gradient accuracy needed.
problem Optimizing complex functions with limited gradient accuracy.
method Hessian averaging and adaptive gradient sampling methods.
result Improved convergence rates for various function types.
Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in practice. Motivated by this, we establish a new setup, called Continuous Online Learning (COL), where the gradient of online loss function cha…
Quantum algorithm speeds up Gibbs partition function estimation.
problem Estimating partition functions in sublinear time.
method Sublinear-time quantum algorithm using quantum phase and amplitude estimation.
result First sublinear-time speed-up for partition function estimation.
The incremental aggregated gradient algorithm is popular in network optimization and machine learning research. However, the current convergence results require the objective function to be strongly convex. And the existing convergence rates are also limited to linear convergence. Due to the mathematical techniques, th…
We provide a general construction of time-consistent sublinear expectations on the space of continuous paths. It yields the existence of the conditional G-expectation of a Borel-measurable (rather than quasi-continuous) random variable, a generalization of the random G-expectation, and an optional sampling theorem that…
Gradient descent converges linearly in finite-width networks with positive NTK and compatible conditions.
problem Local convergence of gradient descent in finite-width networks.
method Positive Neural Tangent Kernel (NTK), local Polyak-Łojasiewicz inequality, fixed-step containment in Locally Quasi-Convex Region (LQCR).
result Linear convergence achieved under specific conditions.
This paper improves understanding of GAIL's generalization and computational efficiency.
problem Understanding the theoretical properties of GAIL, especially its generalization and computational aspects.
method Investigates GAIL's theoretical properties, showing guarantees for generalization and computational efficiency.
result GAIL can be efficiently solved by stochastic first order optimization algorithms with sublinear convergence.