Cosine schedule is optimal for discrete diffusion models.
problem Choosing the best discretization schedule for diffusion models.
method Optimized using Fisher-Rao geometry.
result Cosine schedule is Fisher-Rao optimal.
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “discrete schedules”
Proposes an automatic cyclical scheduling for gradient-based discrete sampling.
problem Gradient-based sampling in high-dimensional models can get stuck in local modes.
method Cyclical step size and balancing schedules with automatic hyperparameter tuning.
result Proves non-asymptotic convergence and inference guarantees for general discrete distributions.
AutoLoss learns optimal schedules for alternating optimization tasks.
problem Optimizing different task objectives with alternating updates.
method Meta-learning framework to learn and determine the optimization schedule.
result AutoLoss improves convergence quality on multiple ML tasks.
This study shows how DDPM can be represented by the OU process.
problem Designing optimal noise schedules for DDPM.
method Formal equivalence between DDPM and OU process, heuristic designs based on Fisher Information.
result Fisher-Information-motivated schedule corresponds to cosine noise schedule.
Withdrawal Success Optimizationq-fin.PM
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.
Masking diffusion outperforms other discrete diffusion models by incorporating jump times into the model.
problem Improving the performance of discrete diffusion models.
method Conditioning on the jump schedule of discrete Markov processes.
result Schedule-conditioned discrete diffusion (SCUD) models outperform classical and masking diffusion models.
This paper optimizes diffusion schedules for better sampling from data distributions.
problem Choosing an optimal discretization schedule for denoising diffusion models.
method Adaptive algorithm that selects an optimal schedule based on a work cost measure.
result The learned schedule recovers and outperforms manually tuned schedules.
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.
Efficient algorithm approximates discrete random variables with minimal Kolmogorov distance.
problem Estimating the probability of missing deadlines in series-parallel schedules.
method An efficient algorithm that computes a random variable with minimal Kolmogorov distance to a given discrete random variable.
result The algorithm efficiently approximates the probability of missing deadlines with minimal Kolmogorov distance.
New error bound for diffusion models without dimensionality constraints.
problem Error estimation in diffusion generative models without dimensionality constraints.
method Derive dimension-free error bound using a smooth test functional.
result Explicit, dimension-free bound on generated vs true data distributions.
LSD distills high-quality samplers for DDMs with fewer steps.
problem Inefficient sampling in DDMs leads to low quality and high computational cost.
method LSD employs a distillation approach to train fast samplers with learnable coefficients and time schedules.
result LSD+ achieves higher sampling quality with fewer steps compared to existing samplers.
MDMs train to decode tokens in a random order, which affects performance; we show they can be optimized for a favorable order.
problem Performance of MDMs is affected by the random order in which tokens are decoded.
method We show that MDMs can be optimized for a favorable decoding order by equipping their continuous-time variational objective with multivariate noise schedules.
result MDMs can be decomposed into a weighted auto-regressive losses over orders, making them auto-regressive models with learnable orders.
New model optimizes oil product distribution via pipelines.
problem Optimizing oil product distribution via pipelines.
method Discrete-time mixed integer linear programming model.
result Significant reductions in pipeline operational cost.
Survey of automated algorithm selection for various problems.
problem Selecting the best algorithm for each problem instance.
method Exploiting performance complementarity among algorithms.
result Major improvements in solving discrete combinatorial problems.
Enhances gradient-based discrete samplers with parallel tempering for multimodal distributions.
problem Local minima in high-dimensional, multimodal discrete distributions.
method Combines parallel tempering with discrete Langevin proposal, using Metropolis criterion for swaps.
result Significantly faster mixing and better sampling from complex distributions.
LADD models improve discrete diffusion for faster language generation.
problem Practical discrete diffusion models ignore cross-token dependencies, degrading performance.
method Introduces a learnable auxiliary latent channel, diffusing over the joint (token, latent) space.
result LADD models yield improvements on unconditional generation metrics.
CR-AIS improves AIS efficiency by constant rate annealing.
problem Efficiently sample from intractable distributions.
method Constant rate annealing schedule for AIS.
result CR-AIS outperforms existing Adaptive AIS methods.
ADCMs adaptively discretize CMs for efficient training.
problem Manual discretization schemes cause repeated adjustments for different noise schedules and datasets.
method Unified framework with optimization problem, local and global consistency constraints, and Gauss-Newton method.
result Significantly improve training efficiency and generative performance of CMs.
New method schedules learning rate without stopping time, outperforming existing methods.
problem Learning rate schedules that require stopping time are outperformed.
method Schedule-Free approach that avoids stopping time and introduces no additional hyper-parameters.
result Exhibits state-of-the-art performance across various problems.
This paper proposes a method to select project schedules with the lowest risk.
problem Selecting schedules that meet project deadlines while minimizing risk.
method Integrating aleatory uncertainty into project scheduling to quantify and compare risks.
result Proposes a method to select schedules with the lowest risk.
Maximizing withdrawal success in a pooled annuity fund with multiple annuitants.
problem Optimizing withdrawal success in a pooled annuity fund with homogeneous annuitants.
method Maximizing the probability of completing withdrawals until death over portfolio weight functions.
result Increasing the number of annuitants can significantly increase the maximum probability of withdrawal success.
Optimizes financial auditor schedules to reduce time and costs.
problem Efficiently scheduling financial auditors with multiple constraints.
method Used Integer Linear Programming and compared two exact formulations.
result Multi-commodity network flow formulation is 24 times faster.
ScheduleFree+ improves large language model training without schedules or learning rates.
problem Scaling up Schedule-Free Learning to large language models.
method Learning-rate-free and schedule-free method for training large language models.
result ScheduleFree+ outperforms SOTA schedules by 31% at 1000 tokens per parameter.
Optimal learning rate schedules derived for various tasks.
problem Inadequate learning rate schedules in practice compared to theory.
method Refined analysis of learning rate schedules for optimization algorithms.
result Derives new problem-adaptive learning rate schedules.
Sharp 2-Wasserstein bounds for DDPMs derived from Föllmer process.
problem Sampling error bounds for DDPMs in 2-Wasserstein distance.
method Lipschitz-type conditions on score function, Föllmer process, and log-concave target distributions.
result Sharp upper bounds for DDPMs in 2-Wasserstein distance, optimal in dimension and steps.
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.
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.
Deep RL optimizes lab test scheduling for better patient outcomes and cost savings.
problem Redundant lab tests lead to cost and patient discomfort.
method Deep reinforcement learning for optimal scheduling.
result Deep RL policy outperforms heuristic scheduling in both accuracy and cost.
Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspectivestat.ML
Paper explores how Rectified Flow adapts to low-dimensional data.
problem Improving sampling efficiency in low-dimensional data.
method Investigates Rectified Flow's adaptation to low-dimensional support and introduces a stochastic version.
result Shows improved sampling efficiency with complexity.
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.
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.
An Analysis of the Value of Information when Exploring Stochastic, Discrete Multi-Armed Banditscs.AI
In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards. High amounts of policy …
Adaptive scheduling improves multilingual neural machine translation models.
problem Training models on multiple tasks with uniform or proportional sampling leads to poor performance trade-offs.
method Exploring non-adaptive and adaptive task scheduling, including implicit schedules.
result Adaptive schedules improve model performance for low-resource tasks without negatively affecting high-resource tasks.
NESA learns user preferences and calendar contexts for efficient event scheduling.
problem Challenges in understanding user preferences and complex calendar contexts for automated event scheduling.
method Leverages deep neural networks to learn user preferences and calendar context from raw online calendars.
result Significantly outperforms previous models in personal and multi-attendee event scheduling tasks.
DL2 uses deep learning to optimize resource allocation in DL clusters.
problem Efficient resource scheduling for deep learning clusters is challenging.
method DL2 combines supervised learning and reinforcement learning to dynamically allocate resources.
result DL2 reduces average training completion time by 44.1% compared to fairness scheduler.
Solves the film scheduling and staggered showtimes problem for movie theaters.
problem Maximize attendance and revenue by scheduling films with staggered showtimes.
method Binary integer linear optimization to find optimal schedules for each cluster of neighboring locations.
result Optimal scheduling cannot be done for all locations at once, but must be done for each cluster.
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.
Enhances multi-project scheduling with multiple priority rules.
problem Resource allocation in multi-project scheduling with limited time and resources.
method Simulation-based approach using composite priority rules.
result Increased probability of finding schedules with shortest duration.
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 study introduces anytime learning schedules for large language models without fixed horizons.
problem Training large language models without knowing the total training horizon.
method Theoretical analysis and weight averaging to create anytime learning schedules.
result Theoretical and empirical evidence shows that weight averaging with simple step sizes can achieve comparable final loss to well-tuned cosine schedules.
Improved VAE model for discrete data through augmented training and multiscale approach.
problem Limited capability of VAE in capturing field correlations in structured data.
method Augmented training with generated variants and multiscale VAE with multiple β values.
result Improved generation quality of VAE models through these methods.
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…
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.
Decima uses machine learning to automatically generate efficient scheduling policies.
problem Scheduling data processing jobs on distributed clusters is complex and requires tuning for each workload.
method Decima employs reinforcement learning and neural networks to learn workload-specific scheduling policies without human intervention.
result Decima improves average job completion time by at least 21% compared to hand-tuned heuristics.
Unified continuous diffusion model outperforms discrete alternatives in scalability and quality.
problem Continuous diffusion models were perceived as less scalable than discrete models.
method Reconstructed Plaid model and compared it with modern discrete DLMs, optimizing noise schedule and embeddings via likelihood.
result Unified continuous diffusion model (RePlaid) outperforms discrete models in compute efficiency and quality.
Simplified masked diffusion models improve discrete data generation.
problem Complex model formulations and unclear relationships hinder discrete data generative modeling.
method Developed a simple and general framework for masked diffusion models.
result Models trained on OpenWebText surpass prior diffusion language models and outperform autoregressive models.
The paper analyzes early stopping in linear regression and shows it's equivalent to ridge regularization.
problem Understanding the effect of early stopping on linear regression models.
method Characterization of gradient descent dynamics and analysis of excess risk.
result Early stopped solution is equivalent to minimum norm solution for a generalized ridge regularized problem.
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.