PyTorchKR Papers

최신 논문

총 1,684편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2410.05760공식 코드 · Papers with Code

Training-free Diffusion Model Alignment with Sampling Demons

Aligning diffusion models with user preferences has been a key challenge. Existing methods for aligning diffusion models either require retraining or are limited to differentiable reward functions. To address these limitations, we propose a stochastic optimization approach, dubbed Demon, to guide the denoising process at inference time without backpropagation through reward functions or model retraining. Our approach works by controlling noise distribution in denoising steps to concentrate density on regions corresponding to high rewards through stochastic optimization. We provide comprehensive theoretical and empirical evidence to support and validate our approach, including experiments that use non-differentiable sources of rewards such as Visual-Language Model (VLM) APIs and human judgements. To the best of our knowledge, the proposed approach is the first inference-time, backpropagation-free preference alignment method for diffusion models. Our method can be easily integrated with existing diffusion models without further training. Our experiments show that the proposed approach significantly improves the average aesthetics scores for text-to-image generation. Implementation is available at https://github.com/aiiu-lab/DemonSampling.

arXiv:2410.03760

On the SAGA algorithm with decreasing step

Stochastic optimization naturally appear in many application areas, including machine learning. Our goal is to go further in the analysis of the Stochastic Average Gradient Accelerated (SAGA) algorithm. To achieve this, we introduce a new $\lambda$-SAGA algorithm which interpolates between the Stochastic Gradient Descent ($\lambda=0$) and the SAGA algorithm ($\lambda=1$). Firstly, we investigate the almost sure convergence of this new algorithm with decreasing step which allows us to avoid the restrictive strong convexity and Lipschitz gradient hypotheses associated to the objective function. Secondly, we establish a central limit theorem for the $\lambda$-SAGA algorithm. Finally, we provide the non-asymptotic $\mathbb{L}^p$ rates of convergence.

arXiv:2410.04285

MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times

We investigate the problem of minimizing the expectation of smooth nonconvex functions in a distributed setting with multiple parallel workers that are able to compute stochastic gradients. A significant challenge in this context is the presence of arbitrarily heterogeneous and stochastic compute times among workers, which can severely degrade the performance of existing parallel stochastic gradient descent (SGD) methods. While some parallel SGD algorithms achieve optimal performance under deterministic but heterogeneous delays, their effectiveness diminishes when compute times are random - a scenario not explicitly addressed in their design. To bridge this gap, we introduce MindFlayer SGD, a novel parallel SGD method specifically designed to handle stochastic and heterogeneous compute times. Through theoretical analysis and empirical evaluation, we demonstrate that MindFlayer SGD consistently outperforms existing baselines, particularly in environments with heavy-tailed noise. Our results highlight its robustness and scalability, making it a compelling choice for large-scale distributed learning tasks.

arXiv:2409.20562

SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes

Meshes are ubiquitous in visual computing and simulation, yet most existing machine learning techniques represent meshes only indirectly, e.g. as the level set of a scalar field or deformation of a template, or as a disordered triangle soup lacking local structure. This work presents a scheme to directly generate manifold, polygonal meshes of complex connectivity as the output of a neural network. Our key innovation is to define a continuous latent connectivity space at each mesh vertex, which implies the discrete mesh. In particular, our vertex embeddings generate cyclic neighbor relationships in a halfedge mesh representation, which gives a guarantee of edge-manifoldness and the ability to represent general polygonal meshes. This representation is well-suited to machine learning and stochastic optimization, without restriction on connectivity or topology. We first explore the basic properties of this representation, then use it to fit distributions of meshes from large datasets. The resulting models generate diverse meshes with tessellation structure learned from the dataset population, with concise details and high-quality mesh elements. In applications, this approach not only yields high-quality outputs from generative models, but also enables directly learning challenging geometry processing tasks such as mesh repair.

arXiv:2409.17107공식 코드 · Papers with Code

Non-asymptotic convergence analysis of the stochastic gradient Hamiltonian Monte Carlo algorithm with discontinuous stochastic gradient with applications to training of ReLU neural networks

In this paper, we provide a non-asymptotic analysis of the convergence of the stochastic gradient Hamiltonian Monte Carlo (SGHMC) algorithm to a target measure in Wasserstein-1 and Wasserstein-2 distance. Crucially, compared to the existing literature on SGHMC, we allow its stochastic gradient to be discontinuous. This allows us to provide explicit upper bounds, which can be controlled to be arbitrarily small, for the expected excess risk of non-convex stochastic optimization problems with discontinuous stochastic gradients, including, among others, the training of neural networks with ReLU activation function. To illustrate the applicability of our main results, we consider numerical experiments on quantile estimation and on several optimization problems involving ReLU neural networks relevant in finance and artificial intelligence.

arXiv:2409.15734

Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models

In this work, we consider solving optimization problems with a stochastic objective and deterministic equality constraints. We propose a Trust-Region Sequential Quadratic Programming method to find both first- and second-order stationary points. Our method utilizes a random model to represent the objective function, which is constructed from stochastic observations of the objective and is designed to satisfy proper adaptive accuracy conditions with a high but fixed probability. To converge to first-order stationary points, our method computes a gradient step in each iteration defined by minimizing a quadratic approximation of the objective subject to a (relaxed) linear approximation of the problem constraints and a trust-region constraint. To converge to second-order stationary points, our method additionally computes an eigen step to explore the negative curvature of the reduced Hessian matrix, as well as a second-order correction step to address the potential Maratos effect, which arises due to the nonlinearity of the problem constraints. Such an effect may impede the method from moving away from saddle points. Both gradient and eigen step computations leverage a novel parameter-free decomposition of the step and the trust-region radius, accounting for the proportions among the feasibility residual, optimality residual, and negative curvature. We establish global almost sure first- and second-order convergence guarantees for our method, and present computational results on CUTEst problems, regression problems, and saddle-point problems to demonstrate its superiority over existing line-search-based stochastic methods.

arXiv:2409.12328

SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems

Stochastic optimization problems in large-scale multi-stakeholder networked systems (e.g., power grids and supply chains) rely on data-driven scenarios to encapsulate complex spatiotemporal interdependencies. However, centralized aggregation of stakeholder data is challenging due to the existence of data silos resulting from computational and logistical bottlenecks. In this paper, we present SplitVAEs, a decentralized scenario generation framework that leverages variational autoencoders to generate high-quality scenarios without moving stakeholder data. With the help of experiments on distributed memory systems, we demonstrate the broad applicability of SplitVAEs in a variety of domain areas that are dominated by a large number of stakeholders. Our experiments indicate that SplitVAEs can learn spatial and temporal interdependencies in large-scale networks to generate scenarios that match the joint historical distribution of stakeholder data in a decentralized manner. Our experiments show that SplitVAEs deliver robust performance compared to centralized, state-of-the-art benchmark methods while significantly reducing data transmission costs, leading to a scalable, privacy-enhancing alternative to scenario generation.

arXiv:2409.09906

Variance-reduced first-order methods for deterministically constrained stochastic nonconvex optimization with strong convergence guarantees

In this paper, we study a class of deterministically constrained stochastic optimization problems. Existing methods typically aim to find an $\epsilon$-stochastic stationary point, where the expected violations of both constraints and first-order stationarity are within a prescribed accuracy $\epsilon$. However, in many practical applications, it is crucial that the constraints be nearly satisfied with certainty, making such an $\epsilon$-stochastic stationary point potentially undesirable due to the risk of significant constraint violations. To address this issue, we propose single-loop variance-reduced stochastic first-order methods, where the stochastic gradient of the stochastic component is computed using either a truncated recursive momentum scheme or a truncated Polyak momentum scheme for variance reduction, while the gradient of the deterministic component is computed exactly. Under the error bound condition with a parameter $\theta \geq 1$ and other suitable assumptions, we establish that these methods respectively achieve a sample and first-order operation complexity of $\widetilde O(\epsilon^{-\max\{\theta+2, 2\theta\}})$ and $\widetilde O(\epsilon^{-\max\{4, 2\theta\}})$ for finding a stronger $\epsilon$-stochastic stationary point, where the constraint violation is within $\epsilon$ with certainty, and the expected violation of first-order stationarity is within $\epsilon$. For $\theta=1$, these complexities reduce to $\widetilde O(\epsilon^{-3})$ and $\widetilde O(\epsilon^{-4})$ respectively, which match, up to a logarithmic factor, the best-known complexities achieved by existing methods for finding an $\epsilon$-stochastic stationary point of unconstrained smooth stochastic optimization problems.

arXiv:2409.09240

Cross-Entropy Optimization for Hyperparameter Optimization in Stochastic Gradient-based Approaches to Train Deep Neural Networks

In this paper, we present a cross-entropy optimization method for hyperparameter optimization in stochastic gradient-based approaches to train deep neural networks. The value of a hyperparameter of a learning algorithm often has great impact on the performance of a model such as the convergence speed, the generalization performance metrics, etc. While in some cases the hyperparameters of a learning algorithm can be part of learning parameters, in other scenarios the hyperparameters of a stochastic optimization algorithm such as Adam [5] and its variants are either fixed as a constant or are kept changing in a monotonic way over time. We give an in-depth analysis of the presented method in the framework of expectation maximization (EM). The presented algorithm of cross-entropy optimization for hyperparameter optimization of a learning algorithm (CEHPO) can be equally applicable to other areas of optimization problems in deep learning. We hope that the presented methods can provide different perspectives and offer some insights for optimization problems in different areas of machine learning and beyond.

arXiv:2409.05282공식 코드 · Papers with Code

Improving Tree Probability Estimation with Stochastic Optimization and Variance Reduction

Probability estimation of tree topologies is one of the fundamental tasks in phylogenetic inference. The recently proposed subsplit Bayesian networks (SBNs) provide a powerful probabilistic graphical model for tree topology probability estimation by properly leveraging the hierarchical structure of phylogenetic trees. However, the expectation maximization (EM) method currently used for learning SBN parameters does not scale up to large data sets. In this paper, we introduce several computationally efficient methods for training SBNs and show that variance reduction could be the key for better performance. Furthermore, we also introduce the variance reduction technique to improve the optimization of SBN parameters for variational Bayesian phylogenetic inference (VBPI). Extensive synthetic and real data experiments demonstrate that our methods outperform previous baseline methods on the tasks of tree topology probability estimation as well as Bayesian phylogenetic inference using SBNs.

arXiv:2409.04636

Notes on Sampled Gaussian Mechanism

In these notes, we prove a recent conjecture posed in the paper by R\"ais\"a, O. et al. [Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimization (2024)]. Theorem 6.2 of the paper asserts that for the Sampled Gaussian Mechanism - a composition of subsampling and additive Gaussian noise, the effective noise level, $\sigma_{\text{eff}} = \frac{\sigma(q)}{q}$, decreases as a function of the subsampling rate $q$. Consequently, larger subsampling rates are preferred for better privacy-utility trade-offs. Our notes provide a rigorous proof of Conjecture 6.3, which was left unresolved in the original paper, thereby completing the proof of Theorem 6.2.

arXiv:2409.00493

Evaluation of Prosumer Networks for Peak Load Management in Iran: A Distributed Contextual Stochastic Optimization Approach

Renewable prosumers face the complex challenge of balancing self-sufficiency with seamless grid and market integration. This paper introduces a novel prosumers network framework aimed at mitigating peak loads in Iran, particularly under the uncertainties inherent in renewable energy generation and demand. A cost-oriented integrated prediction and optimization approach is proposed, empowering prosumers to make informed decisions within a distributed contextual stochastic optimization (DCSO) framework. The problem is formulated as a bi-level two-stage multi-time scale optimization to determine optimal operation and interaction strategies under various scenarios, considering flexible resources. To facilitate grid integration, a novel consensus-based contextual information sharing mechanism is proposed. This approach enables coordinated collective behaviors and leverages contextual data more effectively. The overall problem is recast as a mixed-integer linear program (MILP) by incorporating optimality conditions and linearizing complementarity constraints. Additionally, a distributed algorithm using the consensus alternating direction method of multipliers (ADMM) is presented for computational tractability and privacy preservation. Numerical results highlights that integrating prediction with optimization and implementing a contextual information-sharing network among prosumers significantly reduces peak loads as well as total costs.

arXiv:2408.17387

Bayesian Optimization for Non-Convex Two-Stage Stochastic Optimization Problems

Bayesian optimization is a sample-efficient method for solving expensive, black-box optimization problems. Stochastic programming concerns optimization under uncertainty where, typically, average performance is the quantity of interest. In the first stage of a two-stage problem, here-and-now decisions must be made in the face of uncertainty, while in the second stage, wait-and-see decisions are made after the uncertainty has been resolved. Many methods in stochastic programming assume that the objective is cheap to evaluate and linear or convex. We apply Bayesian optimization to solve non-convex, two-stage stochastic programs which are black-box and expensive to evaluate as, for example, is often the case with simulation objectives. We formulate a knowledge-gradient-based acquisition function to jointly optimize the first- and second-stage variables, establish a guarantee of asymptotic consistency, and provide a computationally efficient approximation. We demonstrate comparable empirical results to an alternative we formulate with fewer approximations, which alternates its focus between the two variable types, and superior empirical results over the state of the art and the standard, na\"ive, two-step benchmark.

arXiv:2408.11084

Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles

We consider stochastic optimization when one only has access to biased stochastic oracles of the objective and the gradient, and obtaining stochastic gradients with low biases comes at high costs. This setting captures various optimization paradigms, such as conditional stochastic optimization, distributionally robust optimization, shortfall risk optimization, and machine learning paradigms, such as contrastive learning. We examine a family of multi-level Monte Carlo (MLMC) gradient methods that exploit a delicate tradeoff among bias, variance, and oracle cost. We systematically study their total sample and computational complexities for strongly convex, convex, and nonconvex objectives and demonstrate their superiority over the widely used biased stochastic gradient method. When combined with the variance reduction techniques like SPIDER, these MLMC gradient methods can further reduce the complexity in the nonconvex regime. Our results imply that a series of stochastic optimization problems with biased oracles, previously considered to be more challenging, is fundamentally no harder than the classical stochastic optimization with unbiased oracles. We also delineate the boundary conditions under which these problems become more difficult. Moreover, MLMC gradient methods significantly improve the best-known complexities in the literature for conditional stochastic optimization and shortfall risk optimization. Our extensive numerical experiments on distributionally robust optimization, pricing and staffing scheduling problems, and contrastive learning demonstrate the superior performance of MLMC gradient methods.

arXiv:2408.09891

Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates

We study convex optimization problems under differential privacy (DP). With heavy-tailed gradients, existing works achieve suboptimal rates. The main obstacle is that existing gradient estimators have suboptimal tail properties, resulting in a superfluous factor of $d$ in the union bound. In this paper, we explore algorithms achieving optimal rates of DP optimization with heavy-tailed gradients. Our first method is a simple clipping approach. Under bounded $p$-th order moments of gradients, with $n$ samples, it achieves $\tilde{O}(\sqrt{d/n}+\sqrt{d}(\sqrt{d}/n\epsilon)^{1-1/p})$ population risk with $\epsilon\leq 1/\sqrt{d}$. We then propose an iterative updating method, which is more complex but achieves this rate for all $\epsilon\leq 1$. The results significantly improve over existing methods. Such improvement relies on a careful treatment of the tail behavior of gradient estimators. Our results match the minimax lower bound in \cite{kamath2022improved}, indicating that the theoretical limit of stochastic convex optimization under DP is achievable.

arXiv:2408.09775

Faster Adaptive Decentralized Learning Algorithms

Decentralized learning recently has received increasing attention in machine learning due to its advantages in implementation simplicity and system robustness, data privacy. Meanwhile, the adaptive gradient methods show superior performances in many machine learning tasks such as training neural networks. Although some works focus on studying decentralized optimization algorithms with adaptive learning rates, these adaptive decentralized algorithms still suffer from high sample complexity. To fill these gaps, we propose a class of faster adaptive decentralized algorithms (i.e., AdaMDOS and AdaMDOF) for distributed nonconvex stochastic and finite-sum optimization, respectively. Moreover, we provide a solid convergence analysis framework for our methods. In particular, we prove that our AdaMDOS obtains a near-optimal sample complexity of $\tilde{O}(\epsilon^{-3})$ for finding an $\epsilon$-stationary solution of nonconvex stochastic optimization. Meanwhile, our AdaMDOF obtains a near-optimal sample complexity of $O(\sqrt{n}\epsilon^{-2})$ for finding an $\epsilon$-stationary solution of nonconvex finite-sum optimization, where $n$ denotes the sample size. To the best of our knowledge, our AdaMDOF algorithm is the first adaptive decentralized algorithm for nonconvex finite-sum optimization. Some experimental results demonstrate efficiency of our algorithms.

arXiv:2408.09074

Gradient-Variation Online Learning under Generalized Smoothness

Gradient-variation online learning aims to achieve regret guarantees that scale with variations in the gradients of online functions, which has been shown to be crucial for attaining fast convergence in games and robustness in stochastic optimization, hence receiving increased attention. Existing results often require the smoothness condition by imposing a fixed bound on gradient Lipschitzness, which may be unrealistic in practice. Recent efforts in neural network optimization suggest a generalized smoothness condition, allowing smoothness to correlate with gradient norms. In this paper, we systematically study gradient-variation online learning under generalized smoothness. We extend the classic optimistic mirror descent algorithm to derive gradient-variation regret by analyzing stability over the optimization trajectory and exploiting smoothness locally. Then, we explore universal online learning, designing a single algorithm with the optimal gradient-variation regrets for convex and strongly convex functions simultaneously, without requiring prior knowledge of curvature. This algorithm adopts a two-layer structure with a meta-algorithm running over a group of base-learners. To ensure favorable guarantees, we design a new Lipschitz-adaptive meta-algorithm, capable of handling potentially unbounded gradients while ensuring a second-order bound to effectively ensemble the base-learners. Finally, we provide the applications for fast-rate convergence in games and stochastic extended adversarial optimization.

arXiv:2408.08499

The Limitations of Model Retraining in the Face of Performativity

We study stochastic optimization in the context of performative shifts, where the data distribution changes in response to the deployed model. We demonstrate that naive retraining can be provably suboptimal even for simple distribution shifts. The issue worsens when models are retrained given a finite number of samples at each retraining step. We show that adding regularization to retraining corrects both of these issues, attaining provably optimal models in the face of distribution shifts. Our work advocates rethinking how machine learning models are retrained in the presence of performative effects.

arXiv:2408.07432

Portfolio and reinsurance optimization under unknown market price of risk

We investigate the optimal investment-reinsurance problem for insurance company with partial information on the market price of the risk. Through the use of filtering techniques we convert the original optimization problem involving different filtrations, into an equivalent stochastic control problem under the observation filtration only, the so-called separated problem. The Markovian structure of the separated problem allows us to apply a classical approach to stochastic optimization based on the Hamilton-Jacobi-Bellman equation, and to provide explicit formulas for the value function and the optimal investment-reinsurance strategy. We finally discuss some comparisons between the optimal strategies pursued by a partially informed insurer and that followed by a fully informed insurer, and we evaluate the value of information using the idea of indifference pricing. These results are also supported by numerical experiments.

arXiv:2408.08101

Stochastic Real-Time Economic Dispatch for Integrated Electric and Gas Systems Considering Uncertainty Propagation and Pipeline Leakage

Gas-fired units (GFUs) with rapid regulation capabilities are considered an effective tool to mitigate fluctuations in the generation of renewable energy sources and have coupled electricity power systems (EPSs) and natural gas systems (NGSs) more tightly. However, this tight coupling leads to uncertainty propagation, a challenge for the real-time dispatch of such integrated electric and gas systems (IEGSs). Moreover, pipeline leakage failures in the NGS may threaten the electricity supply reliability of the EPS through GFUs. To address these problems, this paper first establishes an operational model considering gas pipeline dynamic characteristics under uncertain leakage failures for the NGS and then presents a stochastic IEGS real-time economic dispatch (RTED) model considering both uncertainty propagation and pipeline leakage uncertainty. To quickly solve this complicated large-scale stochastic optimization problem, a novel notion of the coupling boundary dynamic adjustment region considering pipeline leakage failure (LCBDAR) is proposed to characterize the dynamic characteristics of the NGS boundary connecting GFUs. Based on the LCBDAR, a noniterative decentralized solution is proposed to decompose the original stochastic RTED model into two subproblems that are solved separately by the EPS and NGS operators, thus preserving their data privacy. In particular, only one-time data interaction from the NGS to the EPS is required. Case studies on several IEGSs at different scales demonstrate the effectiveness of the proposed method.