Gradient flow method solves for optimal transport starting distributions.
problem Finding the optimal starting distribution for a martingale in optimal transport.
method Following the gradient flow of the Bass functional's L2-lift.
result Gradient flow converges to a minimizer of the Bass functional.
Paper presents algorithm for optimal job selection with dynamic scoring.
problem Optimal job assignment in a sequential selection process with dynamic scores.
method Developed using dynamic programming, with extensions for partial and no-information cases.
result Algorithm allows for optimal job assignment with limited information.
HOFLON automates process start-ups and grade-changes using offline RL and online optimization.
problem Manual operation of start-ups and grade-changes by experts is declining, leaving plant owners without the necessary tacit know-how.
method HOFLON combines offline RL to learn a latent manifold and long-horizon Q-critic, and online optimization to maximize Q-critic while penalizing deviations and excessive variable changes.
result HOFLON outperforms standard offline RL in industrial case studies, delivering better cumulative rewards than historical data.
New method uses limited labeled data and multiple starts to adapt models across domains.
problem Accurate predictions in target domain with few labeled data.
method Fine-tuning from multiple adaptive starts, extending UDA methods.
result Minimax-optimal target performance with limited labeled target data.
This paper analyzes the problem of starting and stopping a Cox-Ingersoll-Ross (CIR) process with fixed costs. In addition, we also study a related optimal switching problem that involves an infinite sequence of starts and stops. We establish the conditions under which the starting-stopping and switching problems admit …
Poor (even random) starting points for learning/training/optimization are common in machine learning. In many settings, the method of Robbins and Monro (online stochastic gradient descent) is known to be optimal for good starting points, but may not be optimal for poor starting points -- indeed, for poor starting point…
Reweighted ALPS improves sampling from multimodal distributions using warm start points.
problem Sampling from multimodal distributions is hard due to exponential mixing times.
method Introduces Reweighted ALPS, a modified Annealed Leap-Point Sampler that uses warm start points.
result First polynomial-time bound for Re-ALPS in a general setting, under a natural assumption.
DiffOPF solves multi-valued OPF problems by sampling from system history.
problem Multi-valued and non-convex OPF problems due to system parameter variability.
method DiffOPF treats OPF as a conditional sampling problem, learning from historical data.
result DiffOPF enables statistically credible warm starts with favorable cost and constraint satisfaction trade-offs.
The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal for one distribution over initial states, but may not be uniformly optimal for others, no matter where the agent starts from. Furthermore, …
Global optimization finds applications in a wide range of real world problems. The multi-start methods are a popular class of global optimization techniques, which are based on the ideas of conducting local searches at multiple starting points. In this work we propose a new multi-start algorithm where the starting poin…
We develop a framework for warm-starting Bayesian optimization, that reduces the solution time required to solve an optimization problem that is one in a sequence of related problems. This is useful when optimizing the output of a stochastic simulator that fails to provide derivative information, for which Bayesian opt…
New algorithm speeds up HMC by generating a warm start in O(d^1/4) iterations.
problem Unclear how many iterations of HMC are needed for high-dimensional sampling.
method Developed a non-Metropolized HMC that generates a warm start in O(d^1/4) iterations, followed by Metropolized HMC.
result Final complexity of O(d^1/4) is the fastest algorithm for high-accuracy sampling under strong log-concavity assumptions.
New method achieves optimal sample complexity without warm-start in bilevel optimization.
problem Optimizing smooth objective functions with fixed point constraints in meta-learning and equilibrium models.
method Fixed point iterations at lower-level and projected inexact gradient descent at upper-level.
result Achieves near optimal sample complexity O(ε−2) and ildeO(ε−1) samples. Warm-start strategies speed up GP inference by 19x.
problem Efficient sequential inference in Gaussian processes.
method Three warm-start strategies exploiting smaller linear systems.
result Warm-starting achieves up to 19x speed-up in convergence.
High-dimensional unimodal distributions can cause MCMC methods to fail.
problem Failure of MCMC methods in high-dimensional unimodal distributions.
method Examples and theoretical analysis of MCMC methods, including Metropolis-Hastings adjusted methods.
result MCMC methods can take an exponential run-time for high-dimensional unimodal distributions.
Algorithm learns halfspaces with Tsybakov noise in polynomial time.
problem PAC learning halfspaces with adversarial noise.
method Reduction to certifying non-optimality, iterative process, warm-start algorithm.
result First polynomial-time algorithm for learning halfspaces with Tsybakov noise.
A lot of effort has been invested into characterizing the convergence rates of gradient based algorithms for non-linear convex optimization. Recently, motivated by large datasets and problems in machine learning, the interest has shifted towards distributed optimization. In this work we present a distributed algorithm …
Optimal SQ bounds for learning binary product distributions and Ising models.
problem Learning binary product distributions and Ising models robustly.
method Statistical Query (SQ) lower bounds for robust learning.
result Optimal SQ lower bounds match known algorithm error guarantees.
Paper improves communication in distributed optimization, reducing worker-to-server data exchanges.
problem Efficiency in server-to-worker communication in distributed optimization.
method MARINA-P, a novel downlink compression method using correlated compressors; M3, combining MARINA-P with uplink compression.
result MARINA-P achieves provably superior server-to-worker communication complexity with increasing number of workers.
Memory-Augmented Meta-Optimization improves cold-start recommendation.
problem Cold-start problem in recommender systems for new users or items.
method Memory-Augmented Meta-Optimization approach with personalized and task-specific memories.
result Significant improvement in cold-start recommendation performance on multiple datasets.
Optimal transport distances help impute missing data.
problem Missing data in real-world datasets.
method Use optimal transport distances as a loss function to impute missing data values.
result OT-based methods match or outperform state-of-the-art imputation methods.
Study robust linear regression without distributional assumptions for heavy-tailed responses.
problem Linear regression with heavy-tailed responses and no distributional assumptions.
method Combining truncated least squares, median-of-means, and aggregation theory to construct a non-linear estimator.
result Achieves excess risk of order d/n with optimal sub-exponential tail. Adaptive SAA solves large-scale stochastic linear programs efficiently.
problem Solving large-scale two-stage stochastic linear programs.
method Iterative algorithm with adaptive sample size and warm starts.
result The algorithm converges to the true solution set with a probabilistic guarantee.
Flow-VQE uses generative flows to optimize VQE efficiently.
problem Complex objective functions and expensive optimization in VQE.
method Generative normalizing flows with parameterized quantum circuits.
result Flow-VQE accelerates convergence and reduces circuit evaluations.
MALA mixes optimally in κ√d steps for log-concave sampling.
problem Sampling from log-concave distributions efficiently.
method Metropolis-Adjusted Langevin Algorithm (MALA) with warm start.
result Optimal minimax mixing time of κ√d iterations for log-concave distributions.
The paper constructs optimal sub-Riemannian geodesics in specific Carnot groups.
problem Optimal paths in sub-Riemannian geometry for certain groups.
method Explicit construction of geodesics using symmetries and the Hadamard technique.
result Identification of cut time and cut locus in the constructed geodesics.
The item cold-start problem seriously limits the recommendation performance of Collaborative Filtering (CF) methods when new items have either none or very little interactions. To solve this issue, many modern Internet applications propose to predict a new item's interaction from the possessing contents. However, it is…
Paper proposes online optimization for uncertain systems using machine learning and DRO.
problem Optimization of uncertain dynamical systems with distributional uncertainty.
method Combines machine learning with Distributional Robust Optimization (DRO) to handle uncertainty.
result Online solutions with probabilistic regret bounds for uncertain systems.
Faster algorithm for sampling logconcave densities in high dimensions.
problem Cubic barrier in sampling logconcave densities from a cold start.
method Two key ingredients: weaker distance sampling and refined log-Sobolev inequality.
result First sub-cubic sampling algorithms for isotropic position.
In distributed statistical learning, N samples are split across m machines and a learner wishes to use minimal communication to learn as well as if the examples were on a single machine. This model has received substantial interest in machine learning due to its scalability and potential for parallel speedup. Howev…
NetDP predicts loan defaults using network data, addressing cold-start issues.
problem Cold-start problem in default prediction for new users.
method Combines unsupervised and supervised network representations, using parameter-server for scalability.
result Effectiveness in cold-start problem, especially for new users.
This work learns exploration policies for unknown distributions using samples and policy gradients.
problem Learning exploration policies for unknown distributions in Bayesian bandits.
method Meta-learning approach parameterizing policies in a differentiable way and optimizing them with policy gradients.
result Effective gradient estimators and variance reduction techniques are derived.
We study a simplification of GAN training: the problem of transporting particles from a source to a target distribution. Starting from the Sobolev GAN critic, part of the gradient regularized GAN family, we show a strong relation with Optimal Transport (OT). Specifically with the less popular dynamic formulation of OT …
Model uses LLMs to process numerical data guided by natural language descriptions.
problem Challenges in integrating prior knowledge into probabilistic models.
method Developed LLM Processes to condition numerical predictive distributions on natural language.
result Improved predictive performance and structured qualitative descriptions.
A new algorithm computes elastic shape distances between curves efficiently.
problem Computing elastic shape distances between curves in high dimensions.
method Dynamic Programming for optimal diffeomorphisms and Kabsch-Umeyama algorithm for optimal rotation matrices.
result Efficient computation of elastic shape distances with improved efficiency for closed curves.
Mango automates hyperparameter tuning for large-scale ML training.
problem Manual hyperparameter tuning is tedious and inefficient for large-scale machine learning.
method Parallel hyperparameter tuning with intelligent search strategies and flexible abstractions.
result Mango achieves comparable performance to Hyperopt while supporting distributed computing.
Accelerates optimal transport computation by 10x with spectral insights.
problem Exponential slow-down of convergence in Entropic Optimal Transport as regularization weakens.
method Spectral insights and spectral warm-start strategy to mitigate convergence issues.
result Faster convergence compared to the reference method Sinkhorn algorithm.
We propose an computational framework for real-time risk assessment and prioritizing for random outcomes without prior information on probability distributions. The basic model is built based on satisficing measure (SM) which yields a single index for risk comparison. Since SM is a dual representation for a family of r…
Gradient descent learns ReLU functions with non-zero bias efficiently.
problem Learning ReLU functions with non-zero bias under Gaussian distributions.
method Gradient descent starting from random initialization.
result Gradient descent achieves near-optimal error with high probability.
The recently developed bag-of-paths (BoP) framework consists in setting a Gibbs-Boltzmann distribution on all feasible paths of a graph. This probability distribution favors short paths over long ones, with a free parameter (the temperature T) controlling the entropic level of the distribution. This formalism enables…
Improved log-concave sampling to O(d1/2) with warm starts.
problem Sampling from strongly log-concave distributions efficiently.
method Warm starts and discretized underdamped Langevin diffusion.
result Achieved O(d1/2) complexity for high-accuracy sampling. The F-measure, which has originally been introduced in information retrieval, is nowadays routinely used as a performance metric for problems such as binary classification, multi-label classification, and structured output prediction. Optimizing this measure is a statistically and computationally challenging problem, s…
Zigzag sampling algorithm efficiently samples from strongly log-concave distributions with low computational cost.
problem Sampling from strongly log-concave distributions efficiently and with low computational complexity.
method Zigzag sampling algorithm with warm start assumption, focusing on gradient evaluations.
result Achieves ε error in chi-square divergence with computational cost of O(κ²d^(1/2)(log(1/ε))^(3/2)) gradient evaluations.
Local search algorithms applied to optimization problems often suffer from getting trapped in a local optimum. The common solution for this deficiency is to restart the algorithm when no progress is observed. Alternatively, one can start multiple instances of a local search algorithm, and allocate computational resourc…
Warm starts improve Gaussian process regression by up to 16x.
problem Optimizing hyperparameters for Gaussian processes.
method Iterative Gaussian processes with warm start optimization.
result Warm starts achieve the same results as conventional methods but significantly speed up computations.
A new method for Gaussian process regression with categorical inputs.
problem Challenges in building a predictive and computationally efficient Gaussian process with categorical inputs.
method Distributional encoding based on maximum mean discrepancy and Wasserstein distance.
result State-of-the-art predictive performance on various datasets.
CDLF predicts product life-cycles in cold-start phases with high accuracy.
problem Forecasting new products in early phases when data is scarce.
method Conditional Diffusion Life-cycle Forecaster (CDLF) combining static descriptors, reference trajectories, and new observations.
result CDLF outperforms classical models in accuracy and probabilistic forecasting.
Bayesian optimization (BO) is a model-based approach for gradient-free black-box function optimization. Typically, BO is powered by a Gaussian process (GP), whose algorithmic complexity is cubic in the number of evaluations. Hence, GP-based BO cannot leverage large amounts of past or related function evaluations, for e…