A new algorithm for solving constrained convex optimization problems efficiently.
problem Constrained convex optimization problems requiring high accuracy solutions.
method Second-Order Conditional Gradient Sliding (SOCGS) algorithm, using projection-free methods to solve quadratic subproblems inexactly.
result Converges quadratically in primal gap after a finite number of linearly convergent iterations.
Policy gradient methods find Nash equilibrium in noisy games.
problem Finding Nash equilibrium in noisy games.
method Policy gradient methods with noise added.
result Policy gradient methods converge to Nash equilibrium in noisy games.
BBVI with STL converges geometrically under perfect specification, with quadratic variance bound.
problem Convergence rate of BBVI with STL estimator.
method Proved geometric convergence rate with quadratic variance bound for BBVI with STL estimator.
result BBVI with STL converges geometrically under perfect variational family specification.
Paper develops methods for non-quadratic loss low-rank matrix recovery.
problem Recovery of low-rank matrices with non-quadratic losses.
method Projected gradient method with a regularity projection oracle.
result Projected gradient method converges globally and linearly.
Study Markov chain gradient descent in Hilbert spaces for quadratic loss.
problem Approximating optimal solutions for quadratic loss functions.
method Developed a Markov chain-based stochastic gradient algorithm in Hilbert spaces.
result Established probabilistic upper bounds on convergence.
Unified analysis of first-order methods for smooth games using IQCs.
problem Certify convergence rates of first-order methods for smooth and strongly-monotone games.
method Adapted integral quadratic constraints (IQCs) to study first-order methods and derive tight upper bounds of convergence rates.
result First global convergence rate for the negative momentum method with O(κ1.5) iteration complexity. New analysis improves SGD for robust and quantile regression with sub-quadratic convergence.
problem Improving SGD for robust and quantile regression with sub-quadratic convergence.
method Piecewise Lyapunov function for first-order differentiable functions.
result First geometrical convergence result for sub-quadratic SGD.
Improved SVRG for quadratic functions achieves better performance and running times.
problem Minimizing quadratic functions with a specific type of Hessian matrix.
method Variant of SVRG algorithm for quadratic functions with improved analysis.
result Improved performance and running times for quadratic functions compared to state-of-the-art methods.
Gaussian belief propagation (GaBP) is an iterative algorithm for computing the mean of a multivariate Gaussian distribution, or equivalently, the minimum of a multivariate positive definite quadratic function. Sufficient conditions, such as walk-summability, that guarantee the convergence and correctness of GaBP are kn…
The DANE algorithm is an approximate Newton method popularly used for communication-efficient distributed machine learning. Reasons for the interest in DANE include scalability and versatility. Convergence of DANE, however, can be tricky; its appealing convergence rate is only rigorous for quadratic objective, and for …
FedExProx's performance is no better than GD for quadratic optimization.
problem Improving convergence of parallel proximal algorithms.
method Developed a novel analysis framework to establish tighter convergence rates.
result FedExProx can outperform GD in non-strongly convex quadratic problems.
Gradient shrinking solitons from Ricci flows terminating in cones.
problem Understanding Ricci flows that terminate in cones.
method Proving properties of Ricci flows with quadratic curvature decay and cone convergence.
result Ricci flows terminating in cones are gradient shrinking solitons.
Investment strategy optimization from discrete to continuous models.
problem Optimizing investment strategies and stopping times in both continuous and discrete settings.
method Characterized value functions via quadratic reflected BSDEs for continuous case, discretized BSDEs for discrete case, and derived uniform convergence rates.
result Uniform convergence and rate from discrete to continuous quadratic reflected BSDEs.
New Q-Newton's method avoids saddle points and converges quadratically.
problem Optimizing functions with saddle points and ensuring convergence guarantees.
method Modified New Q-Newton's method with Backtracking line search.
result Theorem for Morse functions: quadratic convergence to local minima.
Policy gradient converges to globally optimal policy in nearly linear-quadratic systems.
problem Finding optimal policies in nonlinear control systems with partial information.
method Policy gradient algorithm designed for nearly linear-quadratic regulators with small Lipschitz nonlinear components.
result Policy gradient algorithm converges to globally optimal policy with linear rate.
Study shows neural networks trained with GD converge to Gaussian processes with polynomial decay.
problem Understanding convergence of neural networks to Gaussian processes during training.
method Explicit upper bounds on quadratic Wasserstein distance between trained networks and Gaussian approximations.
result Polynomial decay of approximation error with network width and training time.
This work analyzes the convergence rate of unrolling for optimizing quadratic objectives.
problem The challenge of accurately computing Jacobians through optimization.
method Non-asymptotic convergence-rate analysis of unrolled differentiation for gradient descent and Chebyshev method.
result There is a trade-off between fast asymptotic convergence and immediate but slower convergence due to the learning rate.
Study on PG learning for LQ MFC problems with common noise, proving convergence and sample complexity.
problem Optimal policy learning in LQ MFC problems with common noise and entropy regularization.
method Comprehensive error analysis of PG algorithms in both model-based and model-free settings.
result Global linear convergence and sample complexity of PG algorithms in model-free setting.
This research proves that quadratic regularized optimal transport can approximate the Laplace-Beltrami operator on smooth manifolds.
problem Approximating the Laplace-Beltrami operator using optimal transport with quadratic regularization.
method Deriving first-order optimal potentials and analyzing the convergence of discrete Laplace operators.
result The discrete Laplace operators converge to the Laplace-Beltrami operator on smooth manifolds.
We consider the problem of solving a large-scale Quadratically Constrained Quadratic Program. Such problems occur naturally in many scientific and web applications. Although there are efficient methods which tackle this problem, they are mostly not scalable. In this paper, we develop a method that transforms the quadra…
We study the global convergence of generative adversarial imitation learning for linear quadratic regulators, which is posed as minimax optimization. To address the challenges arising from non-convex-concave geometry, we analyze the alternating gradient algorithm and establish its Q-linear rate of convergence to a uniq…
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. Partition functions arise in a variety of settings, including conditional random fields, logistic regression, and latent gaussian models. In this paper, we consider semistochastic quadratic bound (SQB) methods for maximum likelihood inference based on partition function optimization. Batch methods based on the quadrati…
We investigate a class of quadratic-exponential growth BSDEs with jumps. The quadratic structure introduced by Barrieu & El Karoui (2013) yields the universal bounds on the possible solutions. With local Lipschitz continuity and the so-called A_gamma-condition for the comparison principle to hold, we prove the existenc…
New findings show GD converges to a linear interpolator even with quadratic loss function under certain conditions.
problem Understanding convergence of Gradient Descent with quadratic loss functions.
method Parameterized linear regression with quadratic loss function, empirical and theoretical analysis.
result Gradient Descent converges to a linear interpolator even with quadratic loss function under the Edge of Stability regime.
The paper studies how hyperbolic surfaces degenerate along harmonic map rays.
problem The degeneration of hyperbolic surfaces along harmonic map rays.
method Using Teichmüller space and holomorphic quadratic differentials, the authors show convergence of rescaled distance functions to the intersection number with a vertical measured foliation.
result Hyperbolic surfaces along the ray converge to the dual R-tree of the vertical measured foliation in the sense of Gromov-Hausdorff.
Proof of wall-crossing formula using spectral networks.
problem Proving the Kontsevich-Soibelman wall-crossing formula.
method Path-lifting rules for spectral networks, convergence justification.
result Definition and justification of path lifting rules for spectral networks.
Policy gradient methods converge for LQR problems with noisy state dynamics.
problem Finding optimal policies in noisy LQR problems over finite time horizons.
method Policy gradient methods with convergence guarantees for finite time and stochastic state dynamics.
result Global linear convergence for policy gradient methods in LQR problems with weak assumptions.
New algorithm tackles stochastic optimization with inequality constraints.
problem Stochastic optimization with inequality constraints in various applications.
method Active-set stochastic sequential quadratic programming (StoSQP) with a differentiable exact augmented Lagrangian.
result Global convergence for any initialization, KKT residuals converge to zero almost surely.
Paper proposes a new method to detect convergence in SGD.
problem Detecting the transition from fast progress to oscillation in SGD.
method Analyzes Pflug's test and proposes a novel statistical procedure.
result The novel procedure accurately detects stationarity in SGD.
Study resolvent convergence for random matrices with general covariance profiles.
problem Analyzing resolvent convergence for random matrices with non-identically distributed columns.
method Using moments of quadratic forms and deterministic equivalents, the study provides bounds on the trace of matrix products.
result The trace of matrix products is close to the trace of a deterministic equivalent, controlled by matrix norms.
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence is known to be fragile. To understand the instability of actor-critic, we focus o…
QENDy learns quadratic dynamics from nonlinear systems data.
problem Identifying governing equations of highly nonlinear dynamical systems.
method QENDy embeds nonlinear dynamics into a quadratic feature space, requiring trajectory data and preselected basis functions.
result QENDy accurately identifies quadratic dynamics and outperforms SINDy and deep learning methods.
Improved SHB method for faster convergence on strongly-convex quadratics.
problem Understanding and improving the theoretical and practical advantages of SHB.
method Noise-adaptive multi-stage algorithm for SHB with accelerated convergence.
result SHB can achieve accelerated convergence with larger mini-batch sizes.
Study sharp convergence rates of empirical UOT for spatio-temporal point processes.
problem Statistical analysis of UOT for spatio-temporal point processes.
method Empirical plug-in estimators for Kantorovich-Rubinstein distance between intensity measures.
result Sharp convergence rates of empirical UOT in terms of intrinsic dimensions of measures.
New tensor recovery method uses Riemannian optimization on Segre manifold.
problem Recovering low-rank tensors from noisy measurements.
method Riemannian Gradient Descent (RGD) and Riemannian Gauss-Newton (RGN) algorithms over the Segre manifold.
result Proven convergence rates for RGD and RGN under mild noise assumptions.
Paper closes convergence gap for SGD without replacement.
problem Establishing convergence rate for SGD without replacement.
method Analyzes convergence rates for strongly convex and smooth functions.
result Achieves a rate of O(1/T^2 + n^2/T^3) for quadratic sums.
Efficient algorithms compute lambda quantiles for robust portfolio optimization.
problem Computing lambda quantiles efficiently and robustly.
method Λ-Newton-Bis algorithm combining Newton's method and bisection, interval analysis for multiple roots.
result Demonstrated computational efficiency and practical relevance in portfolio optimization.
Paper uses Koopman operator and Nyström method for efficient nonlinear control.
problem Control of nonlinear dynamical systems.
method Combines Koopman operator framework with Nyström approximation for kernel methods.
result Theoretical guarantees on the convergence rates of the approximated Riccati operator and regulator objective.
New method solves stochastic optimization problems with random models.
problem Optimizing stochastic objectives with deterministic constraints.
method Trust-Region Sequential Quadratic Programming with random model.
result Global convergence guarantees for first- and second-order stationary points.
QMME balances cost and speed in convex optimization.
problem Slow convergence of first-order methods and high cost of second-order methods.
method Minimizing quadratic majorants with fixed curvature at each iteration.
result QMME framework achieves sequential convergence under standard assumptions.
New insights into convergence of optimization methods for DAG structure learning.
problem Unclear convergence properties of optimization methods for structure learning.
method Examined the convergence of augmented Lagrangian method (ALM) and quadratic penalty method (QPM) for structure learning.
result Standard convergence result of ALM does not hold in various cases, and QPM is prone to ill-conditioning.
We propose a DC proximal Newton algorithm for solving nonconvex regularized sparse learning problems in high dimensions. Our proposed algorithm integrates the proximal Newton algorithm with multi-stage convex relaxation based on the difference of convex (DC) programming, and enjoys both strong computational and statist…
The paper calculates how fast optimal investment strategies approach CRRA strategies in stochastic factor models.
problem Understanding convergence rates of optimal investment strategies in stochastic factor models.
method Analyzes optimal feedback functions in nonlinear and quadratic term structure models, considering decay of bond prices and power-like utility at high wealth levels.
result Convergence rates of optimal investment strategies to CRRA strategies are determined by bond price decay and power-like utility behavior.
RL solves discrete LQ control with Gaussian optimal policy.
problem Discrete-time linear-quadratic control problem.
method Entropy-based RL to find Gaussian optimal policy.
result RL algorithm solves mean-variance asset-liability management problem.
Study policy gradient for large-agent mean-field control and game in continuous time.
problem Optimal policy learning for large number of agents in continuous-time mean-field systems.
method Policy gradient method applied to linear-quadratic mean-field control and game models.
result Policy gradient converges to optimal solution at a linear rate for both mean-field control and game.
Study on neural networks with quadratic activation functions, focusing on optimization and generalization.
problem Understanding the dynamics and generalization of neural networks with quadratic activation in the over-parametrized regime.
method Teacher-student scenario, empirical loss landscape analysis, gradient descent dynamics, numerical experiments.
result Conditions for the neural network to recover the teacher and achieve small generalization error.
Reconstructing polytopes with fixed facet directions from support function evaluations.
problem Reconstructing polytopes with known facet directions from limited data.
method Least-squares estimate via convex quadratic program, combinatorial characterization for uniqueness, algorithm convergence.
result The least-squares estimate for a fixed simplicial normal fan is a convex quadratic program, and the solution is unique under certain conditions.