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.
Optimizes financial auditor schedules to reduce time and costs.
Belief propagation and its variants are popular methods for approximate inference, but their running time and even their convergence depend greatly on the schedule used to send the messages. Recently, dynamic update schedules have been shown to converge much faster on hard networks than static schedules, namely the res…
Fractal learning rate schedules accelerate vanilla gradient descent.
This work analyzes how often to update the target network in Q-learning.
SALR improves deep learning generalization by dynamically adjusting learning rates.
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,…
Training large machine learning (ML) models with many variables or parameters can take a long time if one employs sequential procedures even with stochastic updates. A natural solution is to turn to distributed computing on a cluster; however, naive, unstructured parallelization of ML algorithms does not usually lead t…
Bayesian method optimizes rescheduling for multipurpose batch processes with incomplete look-ahead information.
New adaptive scheduler improves SAM for better model training.
A major challenge in current optimization research for deep learning is to automatically find optimal step sizes for each update step. The optimal step size is closely related to the shape of the loss in the update step direction. However, this shape has not yet been examined in detail. This work shows empirically that…
We investigate several confounding factors in the evaluation of optimization algorithms for deep learning. Primarily, we take a deeper look at how adaptive gradient methods interact with the learning rate schedule, a notoriously difficult-to-tune hyperparameter which has dramatic effects on the convergence and generali…
New method shows how order of gradient updates impacts stability and convergence in deep learning.
Adaptive optimization algorithms such as Adam are widely used in deep learning. The stability of such algorithms is often improved with a warmup schedule for the learning rate. Motivated by the difficulty of choosing and tuning warmup schedules, recent work proposes automatic variance rectification of Adam's adaptive l…
AIHT improves online high-dimensional quantile regression by separating support discovery and refinement.
Recurrent neural networks can be difficult to train on long sequence data due to the well-known vanishing gradient problem. Some architectures incorporate methods to reduce RNN state updates, therefore allowing the network to preserve memory over long temporal intervals. To address these problems of convergence, this p…
Drop-Muon updates only some layers, speeding up training.
Scheduling the transmission of time-sensitive data to multiple users over error-prone communication channels is studied with the goal of minimizing the long-term average age of information (AoI) at the users under a constraint on the average number of transmissions at the source node. After each transmission, the sourc…
Two algorithms for linear contextual bandits with rare updates achieve optimal regret and efficiency.
Dynamic probabilistic forecasts guide optimal decisions in uncertain processes.
The performance of policy gradient methods is sensitive to hyperparameter settings that must be tuned for any new application. Widely used grid search methods for tuning hyperparameters are sample inefficient and computationally expensive. More advanced methods like Population Based Training that learn optimal schedule…
Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a st…
We propose a variance reduction framework for variational inference using the Multilevel Monte Carlo (MLMC) method. Our framework is built on reparameterized gradient estimators and "recycles" parameters obtained from past update history in optimization. In addition, our framework provides a new optimization algorithm …
AdaS adapts SGD learning rate based on knowledge gain metrics.
New method schedules learning rate without stopping time, outperforming existing methods.
This paper proposes a method to select project schedules with the lowest risk.
ScheduleFree+ improves large language model training without schedules or learning rates.
Cosine schedule is optimal for discrete diffusion models.
Optimal learning rate schedules derived for various tasks.
When training large machine learning models with many variables or parameters, a single machine is often inadequate since the model may be too large to fit in memory, while training can take a long time even with stochastic updates. A natural recourse is to turn to distributed cluster computing, in order to harness add…
The paper optimizes interpolation schedules in generative models to improve sampling accuracy.
New method converts and optimizes sampling schedules for generative models.
This paper proposes a system-agnostic policy for dynamic scheduling.
The paper presents a multi-power law for predicting loss curves across different learning rate schedules.
We propose a robust implementation of the Nerlove--Arrow model using a Bayesian structural time series model to explain the relationship between advertising expenditures of a country-wide fast-food franchise network with its weekly sales. Thanks to the flexibility and modularity of the model, it is well suited to gener…
Current clinical practice to monitor patients' health follows either regular or heuristic-based lab test (e.g. blood test) scheduling. Such practice not only gives rise to redundant measurements accruing cost, but may even lead to unnecessary patient discomfort. From the computational perspective, heuristic-based test …
More and more companies have deployed machine learning (ML) clusters, where deep learning (DL) models are trained for providing various AI-driven services. Efficient resource scheduling is essential for maximal utilization of expensive DL clusters. Existing cluster schedulers either are agnostic to ML workload characte…
Optimal learning rate schedules for SGD in changing data distributions.
Algorithm learns Nash equilibria in stochastic games using entropy-regularized policies.
It is common practice to decay the learning rate. Here we show one can usually obtain the same learning curve on both training and test sets by instead increasing the batch size during training. This procedure is successful for stochastic gradient descent (SGD), SGD with momentum, Nesterov momentum, and Adam. It reache…
Improved stochastic approximation method reduces residual error.
Enhances multi-project scheduling with multiple priority rules.
Learning-rate schedules for large models match optimization theory closely, leading to better training.
The study introduces anytime learning schedules for large language models without fixed horizons.
With online calendar services gaining popularity worldwide, calendar data has become one of the richest context sources for understanding human behavior. However, event scheduling is still time-consuming even with the development of online calendars. Although machine learning based event scheduling models have automate…
A new method for efficiently updating large-scale matrices in real-time.
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.
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…