The paper proposes a method to learn and leverage contextual preference distributions for better decision-making.
problem Heterogeneous and context-dependent human preferences in decision-making problems.
method A sequential learning-and-optimization pipeline using a bounded-variance score function gradient estimator to train a predictive model mapping contextual features to preference distributions.
result The approach reduces average post-decision surprise by up to 25 times compared to risk-averse baselines in a ridesharing environment.
The paper analyzes the efficiency of gradient estimation methods in noisy function evaluations.
problem Estimating gradients of smooth functions using noisy function evaluations.
method Information-theoretic lower bounds and finite difference method analysis.
result The finite difference method is not minimax optimal, suggesting room for improvement in gradient estimation.
We lower bound the complexity of finding ε ε ε -stationary points (with gradient norm at most ε ε ε ) using stochastic first-order methods. In a well-studied model where algorithms access smooth, potentially non-convex functions through queries to an unbiased stochastic gradient oracle with bounded variance, we prove that (i…
New shuffling methods improve convergence without Lipschitz smoothness.
problem Lack of convergence guarantees for shuffling methods under non-Lipschitz conditions.
method Revisit shuffling methods, prove convergence under general bounded variance condition.
result Matched current best-known convergence rates without Lipschitz smoothness.
We introduce a hybrid stochastic estimator to design stochastic gradient algorithms for solving stochastic optimization problems. Such a hybrid estimator is a convex combination of two existing biased and unbiased estimators and leads to some useful property on its variance. We limit our consideration to a hybrid SARAH…
Doubly SGD improves convergence for intractable objective optimization.
problem Optimizing objectives in sum of intractable expectations.
method Doubly SGD with doubly stochastic gradients and independent minibatching.
result Established convergence of doubly SGD under general conditions, including dependent component gradient estimators.
New algorithms solve stochastic variational inequalities without bounded variance assumption.
problem Solving stochastic variational inequalities without bounded variance assumption.
method Developed algorithms for two classes of problems: monotone and structured nonmonotone VIs.
result Oracle complexity of O(ε^-4) for solving VIs with unbounded domains and possibly unbounded variance.
New estimator accurately estimates mean of real-valued distributions without variance knowledge.
problem Estimating the mean of real-valued distributions without prior variance knowledge.
method Introduces a novel estimator that converges sub-Gaussian and works across distributions with bounded variance.
result The estimator achieves accuracy of σ·(1+o(1))√(2log(1/δ)/n) with parameters n, δ, and σ².
New tool for parallel and private stochastic convex optimization reduces query complexity.
problem Parallel and private stochastic convex optimization with reduced query complexity.
method Reweighted Stochastic Query (ReSQue) estimator combined with ball oracle acceleration.
result Achieves state-of-the-art complexities for SCO in parallel and private settings.
Generalizes smoothness conditions for optimization methods.
problem Optimization under non-uniform smoothness conditions.
method Develops a new analysis technique for bounding gradients.
result Obtains convergence rates for gradient descent and Nesterov's method.
This paper analyzes bias-variance trade-off for clipped SFOMs, improving complexity guarantees for heavy-tailed noise.
problem Improving complexity guarantees for stochastic optimization methods with heavy-tailed noise.
method Novel analysis of bias-variance trade-off in gradient clipping for clipped SFOMs.
result Improved complexity guarantees for clipped SFOMs across various tail indices, including infinite mean noise.
Byzantine-resilient federated learning with local iterations and robust mean estimation.
problem Byzantine clients disrupt federated learning with local iterations.
method Local SGD iterations, robust mean estimation, and matrix concentration result.
result Convergence analysis for strongly-convex and non-convex smooth objectives in heterogeneous data settings.
SMG combines shuffling and momentum for non-convex optimization.
problem Non-convex finite-sum optimization problems.
method Shuffling Gradient-based method with momentum.
result Established state-of-the-art convergence rates for SMG.
Paper proposes robust estimators for heavy-tailed data with infinite variance.
problem Developing robust estimators for heavy-tailed data with infinite variance.
method Proposes two robust estimators: ridge log-truncated M-estimator and elastic net log-truncated M-estimator.
result Demonstrates robustness of log-truncated estimations over standard estimations through simulations and real data analysis.
A new optimization method handles Euclidean bounds efficiently.
problem Optimization problems with Euclidean bounds.
method Riemannian limited-memory BFGS method combining quasi-Newton and Riemannian adaptations.
result Outperforms existing methods by several orders of magnitude.
Study on Nesterov's method in stochastic settings, revealing divergence under certain conditions.
problem Understanding Nesterov's method in stochastic settings, especially finite-sum.
method Analysis of Nesterov's accelerated gradient method in stochastic and finite-sum settings.
result Nesterov's method may diverge in finite-sum settings without additional conditions.
New algorithm resists Byzantine attacks in distributed SGD for heterogeneous data.
problem Byzantine attacks in distributed SGD for heterogeneous data.
method Polynomial-time outlier-filtering for robust mean estimation, new matrix concentration result.
result Tolerates up to 25% Byzantine workers and achieves optimal convergence rates.
Improved analysis of extragradient methods for structured VIPs.
problem Efficiently solving large-scale VIPs with weaker conditions.
method Single-call stochastic extragradient methods with expected residual condition.
result Convergence guarantees for quasi-strongly monotone and weak Minty VIPs.
In this paper, we study zeroth-order algorithms for minimax optimization problems that are nonconvex in one variable and strongly-concave in the other variable. Such minimax optimization problems have attracted significant attention lately due to their applications in modern machine learning tasks. We first consider a …
New convergence guarantees for SGDA and SCO under expected co-coercivity.
problem Solving smooth games with stochastic gradient descent-ascent and consensus optimization.
method Introducing expected co-coercivity and proving convergence guarantees for SGDA and SCO.
result Linear convergence of SGDA and SCO to a neighborhood of the solution with constant step-size, and convergence to the exact solution with stepsize-switching rules.
NP-PROV separates mean and variance spaces to improve function uncertainty.
problem Neural Processes fail on out-of-domain tasks due to shared latent space uncertainty.
method Separates mean and variance into function-value-related and position-related latent spaces.
result NP-PROV achieves state-of-the-art likelihood with bounded variance in drifts.
We propose a new stochastic first-order algorithmic framework to solve stochastic composite nonconvex optimization problems that covers both finite-sum and expectation settings. Our algorithms rely on the SARAH estimator introduced in (Nguyen et al, 2017) and consist of two steps: a proximal gradient and an averaging s…
We make three contributions to the theory of k-armed adversarial bandits. First, we prove a first-order bound for a modified variant of the INF strategy by Audibert and Bubeck [2009], without sacrificing worst case optimality or modifying the loss estimators. Second, we provide a variance analysis for algorithms based …
Unified framework for distributed compressed SGD under ( L 0 , L 1 ) (L_0, L_1) ( L 0 , L 1 ) -smoothness.
problem Understanding the joint effect of batch noise, adaptivity, and compression in distributed stochastic optimization.
method Developed a unified theoretical framework using SDEs that incorporate curvature-dependent terms.
result Normalizing updates in DCSGD stabilizes convergence, with normalization degree determined by noise structure and landscape regularity.
Paper proves SHB convergence with biased gradients and approximate step sizes.
problem Establishing convergence of SHB with biased gradients and approximate step sizes.
method Generalizes SHB convergence conditions for biased gradients, approximate step sizes, and block updating.
result Proves convergence of SHB with new conditions for biased gradients and approximate step sizes.
New method improves convergence of SGD for heavy-tailed noise.
problem Heavy-tailed noise in machine learning applications.
method Normalized SGD (NSGD) to handle heavy-tailed noise.
result Improved sample complexity and high-probability convergence.
Optimizes convergence rate of stochastic proximal algorithms for composite convex problems.
problem Solving composite convex optimization problems with composite regularizers.
method Analyzed proximal stochastic gradient method and randomized incremental proximal method under relaxed variance assumptions.
result Proves O ( 1 / T ) O(1/\sqrt{T}) O ( 1/ T ) convergence rate for last iterate of both algorithms under componentwise convexity and smoothness. This paper addresses the problem of online learning in a dynamic setting. We consider a social network in which each individual observes a private signal about the underlying state of the world and communicates with her neighbors at each time period. Unlike many existing approaches, the underlying state is dynamic, and…
New method for robust linear regression in nearly linear time.
problem High-dimensional robust linear regression with adversarial corruption.
method Proposes estimators for two settings with near linear time complexity.
result Achieves optimal sample complexities and recovery guarantees.
We propose a practical Bayesian optimization method over sets, to minimize a black-box function that takes a set as a single input. Because set inputs are permutation-invariant, traditional Gaussian process-based Bayesian optimization strategies which assume vector inputs can fall short. To address this, we develop a B…
Study large deviations in life insurance portfolios without identical distributions.
problem Large deviations in life insurance portfolios with bounded losses and variances.
method Upper bound from standard large deviations, counterexample for full large deviation principle.
result Exponential bound for average loss exceeding a threshold.
New Q-learning algorithm reduces sample complexity for large discount factors.
problem Large discount factors make Q-learning algorithms inefficient.
method Introduces a new Q-learning algorithm with uniformly bounded sample complexity.
result The new algorithm achieves asymptotic covariance that is a quadratic in 1 / ( 1 − ρ ∗ γ ) 1/(1- ρ^* γ) 1/ ( 1 − ρ ∗ γ ) . UCB-V algorithm improves on UCB for MAB problems with variance estimates.
problem Optimizing arm selection in MAB problems with variance information.
method Asymptotic and high probability analysis of UCB-V algorithm.
result UCB-V can exhibit instability in arm-pulling rates but achieves refined regret bounds.
The paper estimates common mean of entangled Gaussians with bounded variances.
problem Estimating common mean of entangled Gaussians with bounded variances.
method Iteratively averaging truncated samples.
result Achieves error $O \left(\frac{\sqrt{n\ln n}}{m}
ight)$ with high probability when m = Ω ( n ln n ) m=Ω(\sqrt{n\ln n}) m = Ω ( n ln n ) . The paper develops a robust algorithm for contextual bandits with heavy-tailed rewards.
problem Contextual bandits with heavy-tailed rewards.
method Develops an algorithm based on Catoni's estimator for robust statistics, applying it to contextual bandits with general function approximation.
result Establishes regret bounds that depend on cumulative reward variance and logarithmically on the reward range and number of rounds.
New method uses momentum to converge in DC optimization with small batches.
problem Lack of convergence properties for stochastic difference-of-convex optimization with small batch sizes.
method Introduces momentum to enable convergence under standard assumptions for any batch size.
result Proves convergence of the algorithm under smoothness and bounded variance assumptions.
New method reduces variance in stochastic optimization with high confidence.
problem Achieving high-probability guarantees in stochastic optimization with weaker noise assumptions.
method Stochastic proximal point method combining proximal subproblem solver and probability booster.
result Demonstrates convergence with low sample complexity under bounded variance assumptions.
SGD converges to global minimum for structured non-convex functions.
problem Optimizing non-convex functions using SGD with slow convergence rates.
method Convergence theorems for SGD on structured non-convex functions, including Quasar and PL conditions.
result SGD converges to global minimum for specific non-convex functions under certain conditions.
Study bounds variance modulation function for K-spider distributions.
problem Bounding variance modulation function for K-spider distributions.
method Used folded moments and total probabilities of spider legs.
result Gave an interval for the variance modulation function.
One LN layer stabilizes neural network extrapolation.
problem Understanding neural networks' extrapolation behavior.
method Applied NTK theory to infinitely-wide networks.
result Adding one LN layer stabilizes network outputs.
New PAC-Bayes bounds for heavy-tailed losses using supermartingales.
problem Extending PAC-Bayes bounds to heavy-tailed losses.
method Using supermartingales and bounded variance assumption.
result PAC-Bayes generalization bounds for heavy-tailed losses.
Enhances gradient estimates for Hermitian Monge-Ampère equations.
problem Improving estimates for Hermitian Monge-Ampère equations.
method Improves gradient estimates using Evans-Krylov and third derivatives estimates.
result Enhanced estimates for second and third order derivatives.
Sharp gradient estimates extended to surfaces with lower Ricci curvature.
problem Rigidity of Cheng-Yau gradient estimates on surfaces with lower Ricci curvature.
method Extending Cheng-Yau gradient estimates to surfaces with lower Ricci curvature bound and higher-dimensional Riemannian manifolds.
result Pointwise Cheng-Yau gradient estimates for higher-dimensional Riemannian manifolds and monotonicity formulas for positive harmonic functions.
Faster policy learning via continuous-time gradients.
problem Efficiently estimating policy gradients for continuous-time systems.
method Approximating continuous-time gradients directly, using adaptive discretization.
result More efficient policy gradient estimator leads to faster learning.
DBQPG improves policy gradient estimation with fewer samples.
problem Accurate policy gradient estimation with limited samples.
method Deep Bayesian Quadrature Policy Gradient (DBQPG).
result DBQPG provides more accurate and less variable gradient estimates.
Improves gradient estimation for discrete distributions with variance reduction techniques.
problem Excessive variance in gradient estimation for discrete distributions.
method Stein operators for discrete distributions and control variates.
result Substantially lower variance in gradient estimation.
Survey paper analyzes curvature estimates for 4D gradient Ricci solitons.
problem Analyzing curvature estimates for different types of 4D gradient Ricci solitons.
method Comparison and new estimates provided for 4D gradient steady Ricci solitons.
result Sharp curvature estimate ∣ R m ∣ ≤ C R |Rm|\le C R ∣ R m ∣ ≤ C R for gradient steady Ricci solitons with positive Ricci curvature. Log-density gradient estimation is a fundamental statistical problem and possesses various practical applications such as clustering and measuring non-Gaussianity. A naive two-step approach of first estimating the density and then taking its log-gradient is unreliable because an accurate density estimate does not neces…