Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

200400600800 · Jun 202019922001200920172026
48 results for optimal schedule

Learning-rate schedules for large models match optimization theory closely, leading to better training.

problem Improving training of large models with optimal learning rates.
method Used a bound from non-smooth convex optimization theory to match learning-rate schedules with practical benefits.
result Extending the learning-rate schedule with optimal learning-rate and transferring it across schedules improves model training.

The paper optimizes interpolation schedules in generative models to improve sampling accuracy.

problem Improving sampling accuracy in generative models with fewer resources.
method Minimizing the averaged squared Lipschitzness of the drift field, using transfer formulas.
result Designed schedules yield more accurate fine-scale statistics at fixed integrator budget.

Schedule-free SGD is optimal for nonconvex optimization problems.

problem Nonconvex optimization in neural networks.
method Developed a general framework for online-to-nonconvex conversion, which converts schedule-free SGD into an effective nonconvex optimization algorithm.
result Schedule-free SGD achieves optimal iteration complexity for nonsmooth, nonconvex optimization problems.

We find optimal learning rate schedules for a random feature model.

problem Choosing optimal learning rates for deep learning models.
method We analyze a powerlaw random feature model trained with SGD, considering optimal schedules as numerical and analytical problems.
result We discover two regimes: easy and hard phases, with different optimal learning rate schedules.

Optimal learning rate schedules for SGD in changing data distributions.

problem Minimizing regret in online learning with changing data distributions.
method Characterized optimal schedules for linear regression, proposed schedules for general convex and non-convex losses, and defined a notion of regret for non-convex losses.
result Upper and lower bounds for regret with constants for convex losses, and an upper bound on total expected regret for non-convex losses.

Annealed importance sampling (AIS) is a common algorithm to estimate partition functions of useful stochastic models. One important problem for obtaining accurate AIS estimates is the selection of an annealing schedule. Conventionally, an annealing schedule is often determined heuristically or is simply set as a linear…

2015-02-18abs ↗pdf ↗

Many machine learning problems involve iteratively and alternately optimizing different task objectives with respect to different sets of parameters. Appropriately scheduling the optimization of a task objective or a set of parameters is usually crucial to the quality of convergence. In this paper, we present AutoLoss,…

2018-10-04abs ↗pdf ↗

New method converts and optimizes sampling schedules for generative models.

problem Optimizing sampling schedules for generative models like flows and diffusions.
method Unified framework for stochastic interpolants, including point mass schedules.
result Demonstrated efficient generation of images with fewer steps.

This work uses reinforcement learning to optimize task scheduling and execution in a dynamic multi-agent warehouse environment.

problem Optimizing task scheduling and execution in a dynamic multi-agent warehouse environment with limited observability.
method Deep reinforcement learning to solve both high-level scheduling and low-level multi-agent execution problems.
result Demonstrates the effectiveness of reinforcement learning in optimizing task scheduling and execution in a dynamic multi-agent environment.

Momentum is a widely used technique for gradient-based optimizers in deep learning. In this paper, we propose a decaying momentum (\textsc{Demon}) rule. We conduct the first large-scale empirical analysis of momentum decay methods for modern neural network optimization, in addition to the most popular learning rate dec…

2019-10-11abs ↗pdf ↗

Maximizes probability of completing investment schedules with optimal portfolio weights.

problem Optimizing probability of completing investment schedules with optimal portfolio weights.
method Computing maximum probability and optimal portfolio weight functions for various rebalancing schedules.
result Noticeable improvements in probability to complete schedules with optimal portfolio weights.

A framework schedules hyperparameters for model-based reinforcement learning, improving performance.

problem Inadequate scheduling of hyperparameters in model-based reinforcement learning.
method Theoretical analysis and AutoMBPO framework to automatically schedule real data ratio and other hyperparameters.
result Training with hyperparameters scheduled by AutoMBPO significantly improves performance.

Study error bounds and optimal schedules for Masked Diffusions with factorized approximations.

problem Analyzing trade-offs between computation and accuracy in Masked Diffusion Models.
method Provided general error bounds and identified optimal schedules based on data distribution information profiles.
result Identified optimal schedule sizes for Masked Diffusion Models.

New research shows many batch selection methods for training work just as well as full batch training.

problem Finding optimal batch selection methods for training.
method Analysis of mini-batch Gradient Descent (GD) and Stochastic GD (SGD) with various batch selection rules.
result All mini-batch schedules, including deterministic ones, generalize optimally for smooth Lipschitz-convex/nonconvex/strongly-convex loss functions.

Reinforcement learning algorithms are gaining popularity in fields in which optimal scheduling is important, and oncology is not an exception. The complex and uncertain dynamics of cancer limit the performance of traditional model-based scheduling strategies like Optimal Control. Motivated by the recent success of mode…

2019-04-02abs ↗pdf ↗

We study the problem of fitting task-specific learning rate schedules from the perspective of hyperparameter optimization, aiming at good generalization. We describe the structure of the gradient of a validation error w.r.t. the learning rate schedule -- the hypergradient. Based on this, we introduce MARTHE, a novel on…

2019-10-18abs ↗pdf ↗

This paper proposes a system-agnostic policy for dynamic scheduling.

problem Dynamic scheduling in changing systems is challenging due to system-specific optimal policies.
method Descriptive policy that learns a system-agnostic scheduling principle.
result System-agnostic meta-learning enables adaptation to unseen system characteristics.

A heuristic minimizes tardy jobs' total weight on single-machine scheduling.

problem Minimizing tardy jobs' total weight on single-machine scheduling.
method Data-driven heuristic combining machine learning and problem-specific characteristics.
result Significantly outperforms state-of-the-art in optimality gap and adaptability.

The paper presents a multi-power law for predicting loss curves across different learning rate schedules.

problem Understanding and optimizing the relationship between model performance and hyperparameters, especially learning rates.
method Proposes a multi-power law that combines power laws based on the sum of learning rates and additional laws for loss reduction due to decay.
result The multi-power law accurately predicts loss curves for unseen learning rate schedules and finds a schedule that outperforms cosine learning rate.

Deep RL improves power control and scheduling for wireless multicast systems.

problem Scalable power control and scheduling for wireless multicast networks.
method Deep reinforcement learning with function approximation using a deep neural network.
result Deep RL can learn optimal power control policies for large systems.

The paper analyzes the InfoNCE loss under different temperature schedules using Langevin dynamics.

problem Understanding the dynamics of InfoNCE loss under fixed versus annealed temperature schedules.
method Modeling embedding evolution under Langevin dynamics on a compact Riemannian manifold, with theoretical guarantees for convergence.
result Slow logarithmic inverse-temperature schedules ensure convergence to globally optimal representations, while faster schedules risk suboptimal minima.

MERLIN tackles multi-objective task scheduling with hierarchical DRL, outperforming existing methods.

problem Optimizing multiple conflicting constraints in multi-objective task scheduling with varying queue sizes.
method Hierarchical deep reinforcement learning approach to manage large queues efficiently.
result MERLIN outperforms existing methods by a large margin (>22%) on multiple queue sizes.

WSqD extends learning rate schedules for large model training without fixed horizons.

problem Fixed learning rate schedules limit training horizon extension.
method WSqD replaces constant stable phase with a shifted inverse-square-root base, retaining linear cooldown.
result WSqD achieves minimax-optimal convergence rate and horizon-independence.

New framework optimizes deep learning training by deferring large batch sizes to late stages.

problem Optimizing batch size scheduling for deep learning training efficiency.
method Introduced the functional scaling law (FSL) framework to analyze and optimize batch size scheduling.
result Large batch sizes can be deferred to late training stages without sacrificing performance.

Learning rate schedule has a major impact on the performance of deep learning models. Still, the choice of a schedule is often heuristical. We aim to develop a precise understanding of the effects of different learning rate schedules and the appropriate way to select them. To this end, we isolate two distinct phases of…

2020-02-24abs ↗pdf ↗

The study optimizes simulated annealing's cooling schedule for better performance.

problem Designing optimal cooling schedules for simulated annealing to improve its performance.
method Analyzed the cooling schedule's impact on simulated annealing's performance and provided sample and simulation complexity results.
result Optimal cooling schedules can be found with a small number of samples, improving the algorithm's runtime or success rate.

Study finds optimal learning rate schedules for sub-100M quantization-aware training across bit-widths.

problem Optimal learning rate schedules for quantization-aware training depend on bit-width.
method Factorial grid testing over bit-width, warmdown fraction, LR magnitude, model size, and seed.
result INT6 QAT requires a different schedule than higher-precision training, falsifying the primary hypothesis.

Adaptive batch size schedules improve language model training efficiency and generalization.

problem Dilemma of choosing batch sizes in large-scale model training.
method General-purpose adaptive batch size schedules compatible with data and model parallelism.
result Adaptive batch size schedules outperform constant batch sizes and heuristic warmup schedules.

ANT improves TS diffusion models by automatically determining noise schedules.

problem Suboptimal performance of TS diffusion models due to lack of domain-specific noise schedules.
method ANT proposes an adaptive noise schedule that automatically determines proper noise schedules for TS datasets based on their statistics.
result ANT achieves state-of-the-art performance on various TS tasks, including forecasting, refinement, and generation.

This paper tackles JSSP with uncertain task durations using DRL.

problem Job Shop Scheduling Problem with uncertain task durations.
method Integrates Graph Neural Networks (GNNs) and Deep Reinforcement Learning (DRL) to generate robust schedules.
result Advances DRL applications to JSSPs, enhancing generalization and scalability.

Logarithmic-time schedules boost large-scale language model training efficiency.

problem Improving performance and efficiency in large-scale language model training.
method Designing time-varying hyperparameters (β1,β2,λ)(β_1, β_2, λ) for AdamW, specifically logarithmic-time scheduling with damping mechanisms.
result ADANA optimizer achieves up to 40% compute efficiency compared to tuned AdamW, with gains persisting as model scale increases.

Seesaw optimizes training by balancing learning rate and batch size, accelerating model pretraining.

problem Optimizing training efficiency for large language models with adaptive optimizers.
method Develops a principled framework for batch-size scheduling, introducing Seesaw which multiplies learning rate by 1/√2 and doubles batch size.
result Empirically, Seesaw reduces wall-clock time by approximately 36% compared to cosine decay, matching theoretical limits.

Analyzes optimal learning rate schedules in high-dimensional non-convex optimization problems.

problem Optimizing high-dimensional non-convex loss landscapes.
method Langevin optimization with learning rate decaying as \(η(t) = t^{-β}\).
result To speed up optimization without getting stuck in saddles, a decay rate \(β < 1\) is optimal, contrary to convex setups where \(β = 1\).