New neural network smoothness constraints improve model performance.
problem Improving model sensitivity to input changes for better generalization and robustness.
method Exploring current smoothness constraints and proposing new flexible definitions.
result Current smoothness constraints lack flexibility and understanding of data, tasks, and learning.
Smoothness analysis of adversarial training reveals L∞ constraints cause more non-smoothness.
problem Non-smoothness of adversarial training loss function.
method Analyzed the smoothness of adversarial training loss function using optimal attacks for model parameters.
result The L∞ constraint causes more non-smoothness than L2 constraint. The paper examines smoothness of value function in consumption-investment models with borrowing constraints.
problem Investor's optimal consumption and investment under consumption-wealth utility and borrowing constraint.
method Second-order smoothness of value function, optimal consumption-investment policy in feedback form, smooth fit condition.
result The value function is second-order smooth and the constraint is binding under certain conditions.
Improves GATs by adding margin-based constraints to prevent over-fitting and over-smoothing.
problem Over-fitting and over-smoothing in GATs.
method Margin-based constraints on attention weights and graph structure.
result Significant improvements over previous GATs on various datasets.
We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization. Unlike most CD methods, we do not assume the constraints to be separable, but let them be coupled linearly. To our knowledge, ours is the first CD method that allows linear coupling constraints, without making th…
Study optimal control with expectation constraint, proving smooth boundary and deriving numerical methods.
problem Optimal control with expectation constraint in a smooth boundary case.
method Uniform ellipticity proof, truncation argument, approximating sequence of PDEs, convergence analysis, numerical schemes.
result Proved smooth boundary and derived numerical methods for optimal control problem.
The paper constrains families of smooth 4-manifolds using Seiberg-Witten invariants.
problem Understanding the topology of families of smooth 4-manifolds.
method Finite dimensional approximation of the Seiberg-Witten monopole map.
result Constructs examples of continuous Zp-actions and shows non-smoothability. Two new methods solve large-scale stochastic convex problems with linear constraints.
problem Solving large-scale stochastic convex optimization problems with many linear constraints.
method Conditional gradient-based methods that process only a subset of constraints at each iteration.
result Rigorous convergence guarantees for the proposed methods.
New findings discourage use of boundary constraints in RL model parameter estimation.
problem Inference of RL model parameters using optimization methods is hindered by boundary constraints.
method Investigated interior point and deterministic direct search algorithms for optimization under smooth vs. boundary constraints.
result Boundary constraints lead to substantial truncation effects, discouraging their use.
Study constraints on diffeomorphisms and homeomorphisms of 4-manifolds with boundary.
problem Constraints on smooth families of 4-manifolds with boundary.
method Use Manolescu's Seiberg-Witten Floer stable homotopy type.
result Inclusion map between diffeomorphisms and homeomorphisms is not a weak homotopy equivalence.
Sharp inequalities in unit ball with constraints on moments.
problem Establishing Sobolev trace inequalities with constraints.
method Constructing smooth test functions for higher order moments.
result Almost optimal Sobolev trace inequalities for 2nd and 4th orders.
Algorithm minimizes loss and constraint violations in online convex optimization with smooth penalties.
problem Minimizing loss and constraint violations in online convex optimization with smooth penalties.
method Projected gradient descent over a set around the current action.
result Both dynamic regret and constraint violation are bounded by the path-length.
Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints. Instead, in many real-world applications, the constraints are derived from side information, such as users' implicit feedbacks and citations among articles. As a result, these constra…
Safe-EF improves federated learning for non-smooth, constrained optimization.
problem Federated learning's communication bottlenecks with high-dimensional model updates.
method Error feedback (EF) for non-smooth convex optimization with safety constraints.
result Safe-EF matches lower complexity bounds and ensures safety constraints.
Adapts PALM to solve NMF with smooth and sparse solutions.
problem Non-negative matrix factorization for dimensionality reduction and source separation.
method Adapted PALM for convex minimization with non-differentiable constraints.
result Solves NMF with smooth and/or sparse solutions.
Study shows only two topological configurations for Spin(7)-manifold fibrations, ruling out smooth Cayley fibrations.
problem Understanding smooth fibrations of compact Spin(7)-manifolds by Cayley submanifolds.
method Geometric and topological constraints from Spin(7)-structure, spinnability criterion, gauge-theoretic input.
result Rules out smooth Cayley fibrations on all known compact torsion-free Spin(7)-manifolds.
Paper tackles efficient BAI in graph-smooth bandits.
problem Best arm identification with graph smoothness constraint.
method Gradient ascent algorithm for sample complexity.
result Asymptotically optimal strategy for BAI.
Study on constraints for topological and smooth realizations of line arrangements and configurations.
problem Investigating constraints on topological and smooth realizations of combinatorial line arrangements and (nk)-configurations. method Exploring constraints via locally-flatly or smoothly embedded 2-spheres, using Furuta's 10/8-Theorem, and G-signature theorem.
result Established a new lower bound for (nk)-configurations, showing n≥k2−5 for topological realizations. The paper classifies energy-minimizing sets in specific domains.
problem Classifying volume-constraint local energy-minimizing sets.
method Proved a Poincaré-type inequality for stable sets.
result Relative boundary of energy-minimizing sets is smooth.
For an arbitrary Frobenius manifold a system of Virasoro constraints is constructed. In the semisimple case these constraints are proved to hold true in the genus one approximation. Particularly, the genus ≤1 Virasoro conjecture of T.Eguchi, K.Hori, M.Jinzenji, and C.-S.Xiong and of S.Katz is proved for smooth pr…
The paper develops methods for sampling from log-concave distributions with constraints.
problem Sampling from log-concave distributions with constraints.
method Randomized midpoint discretization of Langevin diffusions with various projections.
result New convergence guarantees for constrained Langevin algorithms.
Proposes an algorithm for semi-supervised learning with budget constraints.
problem Learning classifiers within test-time budget constraints with limited labeled data.
method Leverages unlabeled data through Laplace smoothing and gradient boosted regression trees.
result First algorithm for semi-supervised budgeted learning.
Estimates multiple linear systems on a graph with smoothness constraints.
problem Joint estimation of multiple linear systems under graph smoothness constraints.
method Proposes estimators for joint estimation of system matrices with error bounds.
result MSE converges to zero as m increases, typically polynomially fast w.r.t m. New algorithms reduce complexity for solving nonconvex optimization problems with stochastic objectives and constraints.
problem Solving nonconvex optimization problems with stochastic objectives and constraints.
method Single-loop quadratic penalty and augmented Lagrangian algorithms with variance reduction techniques.
result Achieved best-known complexity guarantees for solving nonconvex optimization problems with stochastic objectives and constraints.
New constraints rule out some optimal domains for helicity maximisation.
problem Finding a smooth domain of fixed volume that maximizes helicity.
method Established additional geometric constraints on optimal domains.
result Ruled out the optimality of a broad class of solid tori.
Proves generic nondegeneracy for solutions under volume constraint in closed manifolds.
problem Proving nondegeneracy for solutions of the Van der Waals-Allen-Cahn-Hilliard equation.
method Adapting techniques from previous research to prove nondegeneracy.
result Generic nondegeneracy for solutions of the Van der Waals-Allen-Cahn-Hilliard equation under a volume constraint in closed manifolds.
Smoothed analysis shows approximate SOSPs are near-optimal for SDPs with random perturbations.
problem Scalability issues in SDPs due to non-convexity of the factorized approach.
method Smoothed analysis of approximate second-order stationary points (SOSPs) under random perturbations.
result Approximate SOSPs are near-optimal for SDPs with k scaling like the square root of the number of constraints.
Optimal transport framework for density estimation with constraints.
problem Density estimation under expectation constraints.
method Minimizes Wasserstein distance subject to expected value constraints and regularization.
result Framework effectively addresses non-smooth constraints through annealing-like algorithm.
We show the existence of a smooth spherical surface minimizing the Willmore functional subject to an area constraint in a compact Riemannian three-manifold, provided the area is small enough. Moreover, we classify complete surfaces of Willmore type with positive mean curvature in Riemannian three-manifolds.
Counterexample shows state-constrained optimal control problems can have Young measure gaps.
problem Existence of Young measure gaps in state-constrained optimal control problems.
method Provided a counterexample for smooth controllable systems state-constrained to the unit ball.
result Gap occurs in a regular setting with non-convex Lagrangian density.
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. Time-varying mixture densities occur in many scenarios, for example, the distributions of keywords that appear in publications may evolve from year to year, video frame features associated with multiple targets may evolve in a sequence. Any models that realistically cater to this phenomenon must exhibit two important p…
Method approximates efficient frontier of chance-constrained programs.
problem Approximating the efficient frontier of chance-constrained nonlinear programs.
method Stochastic approximation method based on bi-objective viewpoint.
result Converges to stationary solutions of a smooth approximation of the original problem.
New method tackles bilevel optimization with polyhedral constraints.
problem Challenges in bilevel optimization with active-set changes and expensive Hessian inversions.
method Logarithmic barrier smoothing and proxy-gradient algorithm for differentiable approximation.
result Stationarity rates of O(K−2/3) in deterministic setting and O(K−2/5) under stochastic noise. We consider online optimization in the 1-lookahead setting, where the objective does not decompose additively over the rounds of the online game. The resulting formulation enables us to deal with non-stationary and/or long-term constraints , which arise, for example, in online display advertising problems. We propose a…
This paper focuses on convex constrained optimization problems, where the solution is subject to a convex inequality constraint. In particular, we aim at challenging problems for which both projection into the constrained domain and a linear optimization under the inequality constraint are time-consuming, which render …
The paper develops efficient estimators for semi-parametric binary models in distributed computing.
problem Estimation and inference challenges in large-scale data under non-smooth objective functions.
method Proposes one-shot and multi-round divide-and-conquer estimators with adaptive kernel smoothing to relax constraints and achieve superlinear optimization error.
result Establishes quadratic convergence up to optimal statistical error rate and handles dataset heterogeneity and high-dimensional sparse parameters.
Smooth kernel regularizer improves deep neural networks' performance with less data.
problem Deep neural networks need large datasets for effective learning.
method Proposes a smooth kernel regularizer that encourages spatial correlations in convolution kernel weights, learned from previous experience.
result The smooth kernel regularizer improves visual recognition models over an L2 regularization baseline.
COSMO learns DAG structure without acyclicity constraints.
problem Learning DAG structure from data efficiently and without constraints.
method Differentiable approximation of smooth orientation matrix.
result COSMO converges to acyclic solutions without evaluating acyclicity.
We construct low regularity solutions of the vacuum Einstein constraint equations. In particular, on 3-manifolds we obtain solutions with metrics in $H^s\loc$ with s>23. The theory of maximal asymptotically Euclidean solutions of the constraint equations descends completely the low regularity setting. Moreove…
Dynamic angles estimated from noisy measurements over time with smoothness constraints.
problem Recovering angles from noisy pairwise measurements over time.
method Three algorithms for joint estimation of angles under smoothness constraints.
result MSE converges to zero as T increases under milder conditions. We focus on L-spaces for which the boundary maps of the Heegaard Floer chain complexes vanish. In previous paper \cite{Usui}, we collect such manifolds systematically by using the smoothing order on links. In this paper, we classify such L-spaces under appropreate constraint.
A new method for signal processing using piecewise convex fitting.
problem Nonparametric function estimation in signal processing.
method Two-stage adaptive estimate with strong smoothing and constrained smoothing spline fit.
result Piecewise convex fitting reduces MSE and accurately estimates change points.
Study optimal consumption and investment strategies with leverage constraints using Epstein-Zin utility.
problem Optimal portfolio choice under leverage constraints and Epstein-Zin utility.
method Established viscosity solution to HJB equation, demonstrated smoothness, characterized optimal strategies, derived explicit solutions.
result Explicit solutions for optimal consumption and investment strategies under leverage constraints.
First-order method solves stochastic bilevel optimization with linear constraints.
problem Stochastic bilevel optimization with linear constraints and noise.
method Developed a novel framework using gradient-based techniques and smoothed penalty functions.
result Achieved finite-time convergence guarantees for (δ,ε)-Goldstein stationary points. Study bundles over surfaces with specific fibers, determining characteristic numbers and obstructions.
problem Characterizing bundles over surfaces with highly connected fibers.
method Analyzing smooth and topological bundles, providing necessary and sufficient conditions, and computing characteristic numbers.
result Determine characteristic numbers and divisibility constraints on signatures and genera for bundles of this type.
New bounds on Bartnik mass for surfaces with non-negative first eigenvalue.
problem Bounding Bartnik mass for surfaces with spectral non-negativity condition.
method Proving upper bound on Bartnik mass using spectral non-negativity condition.
result Bounded above by √(|S²|_g/16π) under spectral non-negativity.
Houdini finds high-dimensional saddle points under few constraints.
problem Escaping from saddle points in high-dimensional spaces with constraints.
method Gradient descent methods under logarithmic inequality constraints.
result Polynomial time algorithms for escaping saddle points under constraints.