New factorial power constants improve optimization convergence rates.
problem Optimization convergence rates depend on various constants.
method Proposes using factorial powers for defining these constants.
result Factorial powers simplify or improve convergence rates of optimization methods.
LiPopt uses polynomial optimization to estimate neural network Lipschitz constants efficiently.
problem Estimating the Lipschitz constant of neural networks efficiently.
method Sparse polynomial optimization, leveraging network connectivity to reduce complexity.
result Superior estimates of the ℓ∞-Lipschitz constant compared to existing methods. This paper bounds the Lipschitz constants of neural networks and their gradients.
problem Estimating the Lipschitz constant of complex models like neural networks.
method Local upper and lower bounds on Lipschitz constants computed with respect to network parameters.
result It is impossible to derive global upper bounds for the Lipschitz constants of neural networks.
Optimal Poincaré constant estimates on manifolds with ends.
problem Estimating the Poincaré constant on manifolds with ends.
method Heat kernel estimates extended to manifolds with ends, focusing on central balls.
result The Poincaré constant is determined by the second largest end.
Sharp inequality for p-harmonic maps with new optimal constant.
problem Deriving the sharp vectorial Kato inequality for p-harmonic mappings. method Analyzing the inequality for p-harmonic mappings and comparing with scalar valued cases. result Established the optimal constant for p-harmonic maps and enhanced the range of p values for regularity. We determine the best (optimal) constant in the L2 Folland-Stein inequality on the quaternionic Heisenberg group and the non-negative functions for which equality holds.
ECP optimizes expensive functions without knowing Lipschitz constant.
problem Optimizing expensive, non-convex functions with unknown Lipschitz constants.
method ECP minimizes evaluations by focusing on potentially optimal regions, eliminating Lipschitz constant estimation.
result Guaranteed no-regret performance and minimax-optimal regret bounds.
New algorithm reduces individual regret and communication costs in cooperative bandits.
problem Optimal individual and group regret in cooperative multi-agent bandits.
method Integrates a new communication policy into a learning algorithm.
result Achieves optimal individual regret and constant communication costs.
New model OPSS allows constant approximation for maximum coverage problem.
problem Optimizing coverage functions from samples is hard.
method Proposed OPSS model with structured samples.
result Achieved constant approximation for maximum coverage problem.
HALO uses local Lipschitz constants to optimize functions efficiently.
problem Efficiently solving global optimization problems with complex objective functions.
method Hybrid Adaptive Lipschizian Optimization (HALO) algorithm that estimates local Lipschitz constants and balances global and local information.
result HALO outperforms other global optimization algorithms on numerous test functions.
A new algorithm optimizes time-varying functions with non-constant evaluation times.
problem Optimizing functions that change over time with varying evaluation times.
method Proposes a novel time-varying Bayesian optimization algorithm.
result Establishes a regret bound for the proposed algorithm.
We determine the asymptotic behavior of the optimal Lipschitz constant for the systole map from Teichmuller space to the curve complex.
Optimal fees for CFMMs prevent liquidity pools from competing to the bottom.
problem Maximizing liquidity provider returns in CFMMs with multiple pools.
method Theoretical and numerical analysis of Nash equilibria for optimal fees.
result Pure Nash equilibria of optimal fees exist for CFMMs using Uniswap's trade function.
Unique optimal symplectic connections found for submersions.
problem Finding unique optimal symplectic connections for submersions.
method Analytic results and geometric partial differential equations.
result Optimal symplectic connections are unique up to automorphism group.
A simple model for unbalanced optimal transport captures key features.
problem Capturing the main features of unbalanced optimal transport.
method Introducing a metric on the conical extension of diffeomorphisms and studying its properties.
result Total mass evolves with constant acceleration along geodesics.
New framework for Adam-type algorithms with constant β1, improving regret analysis.
problem Theoretical vs. practical use of Adam and variants with constant β1.
method Proposed a novel framework to derive optimal, data-dependent regret bounds with constant β1.
result Optimal, data-dependent regret bounds with constant β1 are achievable without further assumptions.
This work explores representation complexity in RL paradigms, revealing model-based RL as the easiest task.
problem Investigating the representation complexity gap among model-based, policy-based, and value-based RL.
method Demonstrated through analysis of Markov decision processes (MDPs) and introduced new classes of MDPs.
result Representation complexity hierarchy: model-based RL > policy-based RL > value-based RL.
In this paper, we study stable constant mean curvature H surfaces in R3. We prove that, in such a surface, the distance from a point to the boundary is less that π/(2H). This upper-bound is optimal and is extended to stable constant mean curvature surfaces in space forms.
This paper analyzes challenges and solutions in deep learning optimization.
problem Gradient vanishing and exploding issues in deep learning.
method Improvement of gradient flow and constraints on Lipschitz constant.
result Enhanced understanding of Jacobian matrices and Lipschitz constants in deep learning modules.
Theoretical models of the strong nuclear interaction contain unknown coupling constants (parameters) that must be determined using a pool of calibration data. In cases where the models are complex, leading to time consuming calculations, it is particularly challenging to systematically search the corresponding paramete…
Optimal constants for isoperimetric inequalities involving Steklov eigenvalues on surfaces are determined.
problem Determining optimal constants for isoperimetric inequalities involving Steklov eigenvalues on surfaces.
method Analyzing Riemannian surfaces with boundary, considering both given topology and conformal class, and proving inequalities relating conformal invariants and eigenvalues.
result New examples of topological disks realizing optimal constants and inequalities relating conformal invariants of Steklov eigenvalues on surfaces and disks are provided.
The paper studies estimating the normalizing constant using queries to a black-box function in RKHS.
problem Estimating the normalizing constant of a function in a reproducing kernel Hilbert space.
method Combines Bayesian quadrature and Bayesian optimization approaches, considering different levels of difficulty based on the parameter λ.
result The difficulty of estimating the normalizing constant varies between Bayesian quadrature and Bayesian optimization, even with noisy function evaluations.
New algorithm detects changes quickly without knowing parameters, near optimally.
problem Quickest change detection with unknown parameters.
method Leverages theoretical asymptotic properties to derive a scalable approximate algorithm with near optimal performance.
result Detects changes in constant complexity with near optimal performance.
A new method achieves optimal uniformity in designs with minimal flexibility.
problem Achieving optimal uniformity in designs with minimal flexibility.
method Derive a lower bound on the uniformity constant and use a greedy construction to achieve this bound, then extend the scheme for more flexibility.
result A simple greedy construction achieves the optimal uniformity constant.
In this paper, we solve the optimal constant problem in the setting of Ohsawa's generalized L2 extension theorem. As applications, we prove a conjecture of Ohsawa and the extended Suita conjecture, we also establish some relations between Bergman kernel and logarithmic capacity on compact and open Riemann surfaces…
Derives explicit investment strategy with random endowment.
problem Optimal investment with random endowment in a market.
method Duality arguments to derive explicit expression for optimal strategy.
result Explicit expression for optimal trading strategy exists.
Investigates optimal portfolio strategies in markets with latent side information.
problem Investment problem in markets with latent dependence structure and side information.
method Dynamic and constant portfolio strategies, analyzing log-optimal portfolio as benchmark.
result Optimal dynamic strategy growth rate asymptotically converges to constant strategy in stationary markets.
Optimal controls for conformal Laplacian obstacle problems on spheres and manifolds.
problem Optimal control of conformal metrics with constant scalar curvature.
method Analysis of optimal control problem on Riemannian manifolds with positive Yamabe invariant.
result Existence of smooth optimal controls inducing metrics with constant scalar curvature.
Optimal crypto asset routing with CFMMs, including fixed costs.
problem Optimizing order execution on a network of CFMMs with fixed costs.
method Convex optimization for no fixed costs, mixed-integer convex for fixed costs, heuristics for approximate solutions.
result Approximate solutions to optimal routing and arbitrage certification problems.
Paper tackles online optimization with memory and competitive control.
problem Minimizing hitting and switching costs in online optimization problems.
method Optimistic Regularized Online Balanced Descent algorithm.
result Achieves a constant, dimension-free competitive ratio.
This paper optimizes predicting support and resistance levels in financial markets.
problem Optimizing prediction of resistance and support levels in financial markets.
method Assuming a constant elasticity of variance process, the paper derives optimal trading boundaries using the aspiration level hypothesis.
result Optimal trading boundaries serve as predictors of resistance and support levels, located relative to the median interval of the hidden aspiration level.
New PG methods tackle nonconvex optimization with auto-conditioned stepsizes.
problem Optimizing nonconvex functions over convex sets.
method Auto-conditioned projected gradient (AC-PG) methods and stochastic variants.
result Achieved optimal iteration complexity for finding approximate stationary points.
Adaptive sampling improves convergence in heterogeneous distributed optimization.
problem Poor performance of classical SGD and SVRG in heterogeneous distributed settings.
method Adaptive sampling of machines with an adaptive estimate of local Lipschitz constants.
result Significantly accelerates convergence rate from maximum to average Lipschitz constant.
Constructs optimal symplectic connections for Kaehler metrics on holomorphic submersions.
problem Finding canonical relatively Kaehler metrics on holomorphic submersions.
method Extremal Kaehler metrics, optimal symplectic connections, and adiabatic classes.
result Constructs Kaehler metrics with constant scalar curvature and extremal metrics.
New approach achieves optimal rates for differentially private stochastic convex optimization with heavy-tailed gradients.
problem Differentially private stochastic convex optimization with heavy-tailed gradients.
method Reduction-based approach to achieve optimal rates.
result Achieved optimal rates up to logarithmic factors, nearly matching a lower bound.
Stochastic Gradient Descent with a constant learning rate (constant SGD) simulates a Markov chain with a stationary distribution. With this perspective, we derive several new results. (1) We show that constant SGD can be used as an approximate Bayesian posterior inference algorithm. Specifically, we show how to adjust …
The goal of the paper is to design sequential strategies which lead to efficient optimization of an unknown function under the only assumption that it has a finite Lipschitz constant. We first identify sufficient conditions for the consistency of generic sequential algorithms and formulate the expected minimax rate for…
The paper proposes a method to train NNs with a small Lipschitz constant to improve robustness.
problem Neural networks' susceptibility to adversarial perturbations in safety-critical applications.
method The paper introduces a framework to train multi-layer NNs by minimizing their Lipschitz constant, using an optimization scheme based on the Alternating Direction Method of Multipliers.
result The proposed training procedure successfully increases the robustness of neural networks.
We give a concise proof that large classes of optimal (constant curvature or Einstein) pseudo-Riemannian metrics are maximally symmetric within their conformal class.
Study optimal portfolios for many players in a market model with random coefficients.
problem Optimal portfolio selection for many players under relative performance criteria in a market model with random coefficients.
method Game theory and stochastic optimal control, focusing on CARA and CRRA risk preferences, and extending to continuum of players.
result Existence of forward Nash equilibrium and mean field equilibrium for the n-agent game and corresponding mean field stochastic optimal control problem.
We consider a market consisting of one safe and one risky asset, which offer constant investment opportunities. Taking into account both proportional transaction costs and linear price impact, we derive optimal rebalancing policies for representative investors with constant relative risk aversion and a long horizon.
An investor with constant relative risk aversion trades a safe and several risky assets with constant investment opportunities. For a small fixed transaction cost, levied on each trade regardless of its size, we explicitly determine the leading-order corrections to the frictionless value function and optimal policy.
In this paper we provide an explicit formula for the optimal lower bound of Donaldson's J-functional, in the sense of finding explicitly the optimal constant in the definition of coercivity, which always exists and takes negative values in general. This constant is positive precisely if the J-equation admits a solution…
The paper studies optimal maps between hyperbolic surfaces, focusing on their rigidity and obstructions.
problem Finding optimal Lipschitz maps between hyperbolic surfaces and understanding their rigidity and obstructions.
method Introducing deflations, optimal maps to trees that obstruct optimal maps between surfaces, and using a smooth orthogeodesic foliation.
result Deflations are the main obstructions to optimal maps between hyperbolic surfaces, and they are essentially the only ones.
Proposes a new method to learn entire solution paths without discretization.
problem Optimizing a family of problems indexed by hyperparameters.
method Parameterizes the solution path with basis functions and solves a single stochastic optimization problem.
result Uniform error of learned path converges linearly to a constant related to basis expressiveness.
Paper analyzes noisy low-rank matrix optimization, improving RIP bounds and convergence rates.
problem Noisy low-rank matrix optimization with general objective functions.
method Develops new mathematical framework and proves convergence rate under RIP condition.
result Any spurious local solution is close to ground truth when RIP constant is less than 1/3.
Let Σ be a smooth closed hypersurface with non-negative Ricci curvature, isometrically immersed in a space form. It has been proved in \cite{P}, \cite{CZ}, and \cite{C2} that there are some L2 inequalities on Σ which measure the stability of closed umbilical hypersurfaces or more generally, closed hypersurfaces …
Efficiently learns Single-Index Models with constant factor approximation.
problem Learning Single-Index Models under L22 loss with unknown link functions. method An efficient algorithm using alignment sharpness for optimization.
result Achieves constant factor approximation to optimal loss for various distributions and link functions.