New oracles improve stochastic optimization with noisy or biased measurements.
problem Optimizing functions with noisy or biased measurements.
method Introduced biased gradient oracles for stochastic optimization, analyzed RSG and SGD algorithms with these oracles.
result Derived non-asymptotic bounds for convergence rates of algorithms with biased gradient oracles.
Algorithms for bandit convex optimization and online learning often rely on constructing noisy gradient estimates, which are then used in appropriately adjusted first-order algorithms, replacing actual gradients. Depending on the properties of the function to be optimized and the nature of ``noise'' in the bandit feedb…
Piecewise polynomial interpolation-based gradient descent reduces oracle complexity for smooth loss functions.
problem Optimizing empirical risk minimization loss functions
method Piecewise polynomial interpolation-based gradient descent
result Oracle complexity is reduced for smooth loss functions
Analyze SGD with biased gradients, improving convergence rates and accuracy.
problem Analyzing the convergence of SGD with biased gradients.
method Derive convergence results for smooth non-convex functions and quantify the impact of bias magnitude.
result Improved rates under the Polyak-Lojasiewicz condition and insights into how bias magnitude affects accuracy and convergence.
Study on gradient complexity of private optimization with private oracles.
problem Analyzing the efficiency of differentially private optimization algorithms.
method Lower bounds on the number of first-order oracle queries for private optimization.
result Lower bounds on the number of queries for private optimization algorithms, showing a dimension-dependent runtime penalty.
MAMBA learns policies competitive with multiple conflicting oracles.
problem Learning policies from multiple conflicting oracles in reinforcement learning.
method MAMBA uses a gradient estimator in the style of GAE to optimize policies, leveraging demonstrations from multiple weak oracles.
result MAMBA outperforms the state-of-the-art in learning policies competitive with multiple conflicting oracles.
New algorithms ensure reproducibility and optimal convergence in convex optimization.
problem Trade-off between reproducibility and convergence rate in convex optimization.
method Regularization-based algorithms for smooth convex minimization and minimax optimization.
result Achieves optimal reproducibility and near-optimal gradient complexity for various oracle settings.
We provide tight upper and lower bounds on the complexity of minimizing the average of m convex functions using gradient and prox oracles of the component functions. We show a significant gap between the complexity of deterministic vs randomized optimization. For smooth functions, we show that accelerated gradient de…
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.
Gradient-based methods can be biased by distributional asymmetries in bivariate categorical data.
problem Gradient-based causal discovery methods can be biased by distributional asymmetries in bivariate categorical data.
method Identified and examined two distributional biases: Marginal Distribution Asymmetry and Marginal Distribution Shift Asymmetry. Employed two simple models to demonstrate and control these biases.
result Gradient-based methods can be biased by distributional asymmetries, and these biases can be controlled.
Develops accelerated methods for optimization using low-dimensional projected-gradient information.
problem Optimization with low-dimensional projected-gradient information and Nesterov acceleration.
method Randomized-subspace Nesterov accelerated gradient methods for smooth convex and strongly convex optimization.
result Established accelerated oracle-complexity guarantees and unified basis for comparing sketch families.
Gradient descent is efficient for solving feasibility problems with minimal memory and queries.
problem Finding a point in a given set using a memory-constrained algorithm with a separation oracle.
method Oracle complexity lower bounds for gradient descent and other algorithms.
result Gradient descent is Pareto-optimal in the oracle complexity/memory tradeoff for feasibility problems.
CJE calibrates cheap LLM judges against an oracle, achieving high accuracy at a fraction of the cost.
problem Inexpensive LLM judges can produce biased rankings, leading to unreliable outcomes.
method CJE uses a small oracle to calibrate cheap scores, then evaluates at scale with valid uncertainty.
result CJE achieves 99% pairwise ranking accuracy at 14x lower cost compared to a 16x oracle/judge cost ratio.
A quantum reinforcement learning algorithm reduces sample complexity.
problem Quantum reinforcement learning under model-free settings with quantum oracle access.
method Quantum Natural Policy Gradient (QNPG) algorithm replacing random sampling with deterministic gradient estimation.
result QNPG achieves a sample complexity of ildeO(ε−1.5) for queries to the quantum oracle, significantly improving classical lower bound. New algorithm improves gradient-based ERM for smooth convex losses.
problem Empirical risk minimization of smooth, strongly convex loss functions.
method Iterative gradient-based method with local polynomial regression.
result Oracle complexity of O((pε−1)d/(2η)) for our algorithm. New variance-reduction methods solve stochastic composite inclusions.
problem Solving nonmonotone stochastic composite inclusions.
method Developed unbiased and biased variance-reduced estimators for FRBS method.
result Achieved best oracle complexities for finite-sum and expectation settings.
Paper proposes a new method to stabilize noisy gradient algorithms.
problem Stochastic-gradient Langevin algorithms can introduce bias when taming denominators depend on stochastic-gradient realizations.
method Proposes a structure-preserving framework for designing tamed denominators that avoid unnecessary taming and maintain the stabilizing effect of taming.
result The method avoids stationary bias and explains the stationary error split into bias and remaining error.
We present a convergence rate analysis for biased stochastic gradient descent (SGD), where individual gradient updates are corrupted by computation errors. We develop stochastic quadratic constraints to formulate a small linear matrix inequality (LMI) whose feasible points lead to convergence bounds of biased SGD. Base…
Improved algorithm finds second-order stationary points in non-convex optimization.
problem Minimizing non-convex objectives while preserving training data privacy.
method SpiderBoost framework with two gradient oracles: precise and less precise.
result Improved rates for finding second-order stationary points.
Improved complexity for machine learning optimization methods.
problem Optimizing over-parametrized models in machine learning.
method Stochastic conditional gradient methods with interpolation-like conditions.
result Improved oracle complexities for finding optimal solutions.
New biased compression methods lead to faster convergence in distributed learning.
problem Improving convergence rates in distributed learning with biased compression.
method Study of three classes of biased compression operators in distributed learning.
result Biased compressors can lead to linear convergence rates in both single node and distributed settings.
New method improves adversarial robustness of neural networks.
problem Vulnerability of neural networks to adversarial attacks.
method Integrates φ-divergence regularization into distributionally robust risk function.
result Achieves near-optimal sample complexity with efficient stochastic gradient methods.
Develops shuffling gradient-based methods for nonconvex-concave minimax optimization.
problem Nonconvex-concave minimax optimization problems.
method Two shuffling gradient-based algorithms for nonconvex-linear and nonconvex-strongly concave settings.
result Achieves state-of-the-art oracle complexity in nonconvex optimization and best-known complexity bounds for nonconvex-strongly concave setting.
This paper analyzes SGD with biased gradients for deep learning models.
problem Analyzing SGD with biased gradients for deep learning models.
method Non-asymptotic analysis of SGD with adaptive steps for non-convex smooth functions.
result Adagrad, RMSProp, and AMSGRAD converge to critical points at a similar rate to unbiased case.
We present a generic framework for trading off fidelity and cost in computing stochastic gradients when the costs of acquiring stochastic gradients of different quality are not known a priori. We consider a mini-batch oracle that distributes a limited query budget over a number of stochastic gradients and aggregates th…
Accelerates ERM problems with LPI-GD and improved oracle complexity.
problem Empirical Risk Minimization (ERM) problems with strong convexity and smoothness.
method Local Polynomial Interpolation-based Gradient Descent (LPI-GD) and accelerated methods.
result Oracle complexity improved to $ ilde{O}\left(\sqrtσ m^d \log(1/\varepsilon)
ight)$.
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.
A number of optimization approaches have been proposed for optimizing nonconvex objectives (e.g. deep learning models), such as batch gradient descent, stochastic gradient descent and stochastic variance reduced gradient descent. Theory shows these optimization methods can converge by using an unbiased gradient estimat…
A new biased gradient descent method for conditional stochastic optimization.
problem Challenges in constructing unbiased gradient estimators for conditional stochastic optimization.
method Proposes a biased stochastic gradient descent (BSGD) algorithm and analyzes its sample complexities.
result Establishes sample complexities of BSGD for various objectives and shows that BSpiderBoost matches the lower bound complexity.
The paper analyzes time-dependent streaming data with biased gradient estimates and proposes improved stochastic optimization methods.
problem Stochastic optimization in a streaming setting with time-dependent and biased gradient estimates.
method Analysis of several first-order methods including SGD, mini-batch SGD, and time-varying mini-batch SGD, along with their Polyak-Ruppert averages.
result Time-varying mini-batch SGD methods can break long- and short-range dependence structures, and biased SGD methods can achieve comparable performance to their unbiased counterparts.
RPI combines imitation and reinforcement learning to improve policies efficiently.
problem High sample complexity in reinforcement learning.
method Active interleaving between imitation and reinforcement learning, using oracle queries for exploration.
result RPI outperforms existing methods across various domains.
Paper develops a TR-SSQP method for noisy optimization with heavy-tailed noise.
problem Optimization problems with stochastic objectives and heavy-tailed noise.
method Trust-Region Stochastic Sequential Quadratic Programming (TR-SSQP) method.
result Achieves high-probability first-order and second-order stationarity bounds for heavy-tailed noise.
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.
With recent advances in high throughput technology, researchers often find themselves running a large number of hypothesis tests (thousands+) and esti- mating a large number of effect-sizes. Generally there is particular interest in those effects estimated to be most extreme. Unfortunately naive estimates of these effe…
Algorithm samples composite logconcave densities efficiently.
problem Sampling from composite logconcave densities efficiently.
method Uses a restricted Gaussian oracle and gradient queries.
result Achieves strong total variation distance guarantees.
The study analyzes implicit biases in neural networks using backward error analysis.
problem Analyzing implicit biases in multitask and continual learning settings.
method Backward error analysis to compute implicit training biases, deriving modified losses with three terms.
result The conflict term, measuring gradient alignment, is a new quantity in continual learning.
This paper tackles bandit optimization with a new pairwise comparison oracle for unknown strongly concave functions.
problem Maximizing an unknown strongly concave function over T periods with a biased pairwise comparison oracle.
method Introduced a discretization technique and local polynomial approximation to relate the problem to linear bandits. Developed a tournament successive elimination technique to localize the discretized cell and run LinUCB algorithm on cells.
result Established optimal regret bounds and improved state-of-the-art results in operations management problems.
Unified framework for understanding GRPO as U-statistic.
problem Theoretical properties of GRPO remain less studied.
method Unified framework through classical U-statistics.
result GRPO is asymptotically equivalent to an oracle policy gradient algorithm.
A new hybrid algorithm reduces stochastic gradient evaluations for nonconvex optimization.
problem Solving stochastic composite nonconvex optimization problems efficiently.
method Proposes a new hybrid variance-reduced proximal gradient method with a stochastic gradient estimator.
result Achieves optimal stochastic oracle complexity bound with one less gradient evaluation.
Designing deterministic denominators for SGLD stabilizes large drifts.
problem Stabilizing large drifts in SGLD
method Using state-dependent envelopes and empirical quantiles for activation thresholds
result Proxy-quantile denominators are close to oracle-score behavior and improve deterministic taming choices
Researchers compare different gradient methods for ridge regression, finding conjugate gradients have similar performance.
problem Comparing statistical properties of different gradient methods in ridge regression.
method Explicit non-standard error decomposition to bound prediction error of conjugate gradient iterates.
result Conjugate gradient iterates share optimality properties with gradient flow and ridge regression up to a constant factor.
A new method reduces the complexity of decentralized optimization.
problem Decentralized stochastic non-convex optimization over a network.
method GT-HSGD, a hybrid variance-reduced method.
result Achieves an oracle complexity of O(n^(-1)ε^(-3)) for small ε.
New method removes oracle and reduces memory usage for robust MDPs.
problem Applying robust MDPs in practice due to model estimation and oracle requirements.
method Transformed robust MDPs into an alternative form allowing stochastic gradient methods and model-free approach.
result Sample-efficient algorithm with lower storage requirement and no oracle.
In this paper, we propose to combine imitation and reinforcement learning via the idea of reward shaping using an oracle. We study the effectiveness of the near-optimal cost-to-go oracle on the planning horizon and demonstrate that the cost-to-go oracle shortens the learner's planning horizon as function of its accurac…
New algorithm solves complex optimization problems without needing projections.
problem Optimizing nested functions under convex constraints with noisy evaluations.
method Projection-free conditional gradient-type algorithm for smooth stochastic multi-level composition optimization.
result The algorithm achieves ε-stationary solutions with complexity bounds independent of ε and T. We study the convergence rate of stochastic optimization of exact (NP-hard) objectives, for which only biased estimates of the gradient are available. We motivate this problem in the context of learning the structure and parameters of Ising models. We first provide a convergence-rate analysis of deterministic errors fo…
Study reveals biases in gradient descent for GLNs, improving neural network performance.
problem Understanding and improving the inductive biases of deep neural networks.
method Derive infinite-time training limit of gated linear networks and generalize to other networks.
result Theoretical framework captures key inductive biases of ReLU networks.
A new federated learning algorithm improves on existing methods by exploiting data smoothness.
problem Federated learning optimization with smooth loss functions.
method Federated Low Rank Gradient Descent (FedLRGD) algorithm.
result FedLRGD outperforms Federated Averaging (FedAve) in federated oracle complexity under certain conditions.