The study sets criteria for efficient communication in distributed online learning.
problem Achieving optimal learning performance while minimizing communication in distributed online learning.
method Formal criteria based on the intuition that in the worst case, every input is essential for learning performance and must be exchanged.
result The criteria hold for a simplified version of a previously published protocol, providing a communication bound that scales with the serialized prediction problem's hardness.
Algorithm beats best constant rebalancing portfolio in long-term investment.
problem Poor performance of learning algorithms in online portfolio optimization.
method Leverages serial dependence in asset returns without distributional assumptions.
result Strategy asymptotically grows to highest rate among all strategies.
New rules control false discoveries in online anomaly detection for time series data.
problem Controlling false discoveries in anomaly detection for time series data.
method Novel online false discovery rate control (FDRC) rules for time series anomaly detection.
result Ensures high power in detecting anomalies even when the alternative is rare and test statistics are serially dependent.
A new algorithm for competing agents in a two-sided market setting.
problem Decentralized competition between agents in a two-sided market with unknown valuations.
method UCB-D3 algorithm for UCB with Decentralized Dominant-arm Deletion.
result UCB-D3 is order optimal and achieves a new regret lower bound.
Serial problems can't be efficiently parallelized, affecting machine learning models.
problem Inefficiency of parallelization in inherently serial problems.
method Formalized distinction in complexity theory, demonstrated with diffusion models.
result Diffusion models cannot solve inherently serial problems.
Computational efficiency is an important consideration for deploying machine learning models for time series prediction in an online setting. Machine learning algorithms adjust model parameters automatically based on the data, but often require users to set additional parameters, known as hyperparameters. Hyperparamete…
Complex structures are typical in machine learning. Tailoring learning algorithms for every structure requires an effort that may be saved by defining a generic learning procedure adaptive to any complex structure. In this paper, we propose to map any complex structure onto a generic form, called serialization, over wh…
Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize. In this pap…
Online VSMC efficiently learns SSM parameters in streaming data.
problem Parameter learning and latent state inference in state-space models.
method Combines particle methods and variational inference for online learning.
result Online VSMC achieves efficient, entirely on-the-fly parameter estimation and particle proposal adaptation.
Transformers approximate Bayesian posteriors but not exactly.
problem Bayesian accounts of in-context learning face challenges due to task-preserving order changes in transformers.
method Showed that excess prequential code length is exactly cumulative predictive KL, decomposing expected regret into order-averaged predictor and order-averaging gain.
result Transformers approximate Bayesian posteriors but not exactly, priced by log loss.
We study the relation between serial correlation of financial returns and volatility at intraday level for the S&P500 stock index. At daily and weekly level, serial correlation and volatility are known to be negatively correlated (LeBaron effect). While confirming that the LeBaron effect holds also at intraday level, w…
Stochastic momentum methods trade compute efficiency for serial runtime.
problem Stochastic momentum methods trade compute efficiency for serial runtime.
method Stochastic HB and ASGD for consistent linear regression with Gaussian covariates.
result HB preserves SGD-level CE over a larger batch-size window, allowing larger batches to reduce serial runtime until HB reaches its deterministic accelerated scale.
The paper proposes estimators for bid-ask spreads with and without serial dependence.
problem Estimating bid-ask spreads in financial markets with and without serial dependence.
method The authors propose moment-based estimators for bid-ask spreads, considering both geometric Brownian motion and geometric fractional Brownian motion for price dynamics, and Ornstein-Uhlenbeck process for microstructure noise.
result The estimators are consistent and asymptotically normal, and perform well compared to existing approaches on simulated data.
The book chapter discusses tail risk analysis for financial data using extreme value statistics.
problem Serial dependence in financial time series complicates tail risk assessment.
method The approach involves unconditional and conditional quantile forecasting.
result Serial dependence impacts multivariate tail dependence.
We investigate serial correlation, periodic, aperiodic and scaling behaviour of eigenmodes, i.e. daily price fluctuation time-series derived from eigenvectors, of correlation matrices of shares listed on the Johannesburg Stock Exchange (JSE) from January 1993 to December 2002. Periodic, or calendar, components are dete…
This paper takes a deep learning approach to understand consumer credit risk when e-commerce platforms issue unsecured credit to finance customers' purchase. The "NeuCredit" model can capture both serial dependences in multi-dimensional time series data when event frequencies in each dimension differ. It also captures …
Diffusion models explained via cognitive science.
problem Weak sensitivity to noise family and noise level scheduling.
method Correspondence with serial reproduction in cognitive science.
result Properties of diffusion models explained by cognitive science.
We study the impact of volatility on intraday serial correlation, at time scales of less than 20 minutes, exploiting a data set with all transaction on SPX500 futures from 1993 to 2001. We show that, while realized volatility and intraday serial correlation are linked, this relation is driven by unexpected volatility o…
In practice daily volatility of portfolio returns is transformed to longer holding periods by multiplying by the square-root of time which assumes that returns are not serially correlated. Under this assumption this procedure of scaling can also be applied to contributions to volatility of the assets in the portfolio. …
ParaMonte::Python streamlines Bayesian data analysis with fast Monte Carlo and MCMC routines.
problem Efficiently sampling posterior distributions in Bayesian modeling and data science.
method Serial and MPI-parallelized Markov Chain Monte Carlo (MCMC) routines.
result Automated model calibration and uncertainty quantification in Bayesian analysis.
Recent years have witnessed exciting progress in the study of stochastic variance reduced gradient methods (e.g., SVRG, SAGA), their accelerated variants (e.g, Katyusha) and their extensions in many different settings (e.g., online, sparse, asynchronous, distributed). Among them, accelerated methods enjoy improved conv…
CoT enhances transformer accuracy on serial tasks by enabling serial computation.
problem Improving accuracy of large language models on inherently serial problems.
method Integrating a chain of thought (CoT) into decoder-only transformers to enable serial computation.
result Constant-depth transformers with CoT can solve problems in AC^0, surpassing TC^0 without CoT.
W-RNN improves text classification by extracting serialized text semantics.
problem Semantic constraint in sparse representation classification methods.
method Weighted RNN using word vectors and recurrent neural networks.
result W-RNN outperforms other methods in precision, recall, F1, and loss values.
Proposes rCV to preserve serial correlations in time-series models.
problem Loss of serial correlations in cross-validation for time-series models.
method Form k folds, generate k new partial time-series, reconstruct using imputation/smoothing, build primary models, evaluate performance.
result Avoids loss of serial correlations and preserves non-stationarity in predictions.
In this paper we investigate the adaptive market efficiency of the agricultural commodity futures market, using a sample of eight futures contracts. Using a battery of nonlinear tests, we uncover the nonlinear serial dependence in the returns series. We run the Hinich portmanteau bicorrelation test to uncover the momen…
We consider the problem of fast time-series data clustering. Building on previous work modeling the correlation-based Hamiltonian of spin variables we present an updated fast non-expensive Agglomerative Likelihood Clustering algorithm (ALC). The method replaces the optimized genetic algorithm based approach (f-SPC) wit…
Algorithm achieves comparable performance to fully dynamic data with only a few batches.
problem High-dimensional multi-armed contextual bandits with batched feedback.
method Provable sample-efficient algorithm using batch allocation method.
result Achieves regret bounds comparable to fully sequential setting with only L = O(log T) batches.
MER algorithm speeds up VI solving with Markovian data.
problem Solving stochastic variational inequalities with Markovian data.
method MER algorithm using multi-scale sampling from a Markovian buffer.
result Achieves faster convergence without knowing Markov chain mixing time.
We implement a master-slave parallel genetic algorithm (PGA) with a bespoke log-likelihood fitness function to identify emergent clusters within price evolutions. We use graphics processing units (GPUs) to implement a PGA and visualise the results using disjoint minimal spanning trees (MSTs). We demonstrate that our GP…
Paper introduces Decentralized Non-stationary Competing Bandits ( exttt{DNCB}) for dynamic matching markets.
problem Understanding dynamic two-sided matching markets with competing agents.
method Proposes a decentralized asynchronous learning algorithm ( exttt{DNCB}) for non-stationary environments.
result Obtains sub-linear (logarithmic) regret of exttt{DNCB} in dynamic settings.
Practitioners of Bayesian statistics have long depended on Markov chain Monte Carlo (MCMC) to obtain samples from intractable posterior distributions. Unfortunately, MCMC algorithms are typically serial, and do not scale to the large datasets typical of modern machine learning. The recently proposed consensus Monte Car…
ParaMonte simplifies Monte Carlo simulations for various scientific fields.
problem Efficiently performing Monte Carlo simulations for complex models.
method Unified, high-performance, parallelized library for C, C++, Fortran.
result Automates and streamlines Monte Carlo sampling for arbitrary-dimensional functions.
We present a general framework for accelerating a large class of widely used Markov chain Monte Carlo (MCMC) algorithms. Our approach exploits fast, iterative approximations to the target density to speculatively evaluate many potential future steps of the chain in parallel. The approach can accelerate computation of t…
Serial crystallography is the field of science that studies the structure and properties of crystals via diffraction patterns. In this paper, we introduce a new serial crystallography dataset comprised of real and synthetic images; the synthetic images are generated through the use of a simulator that is both scalable …
The Sharpe ratio, which is defined as the ratio of the excess expected return of an investment to its standard deviation, has been widely cited in the financial literature by researchers and practitioners. However, very little attention has been paid to the statistical properties of the estimation of the ratio. Lo (200…
Estimates Hurst exponent of log-volatility using KS statistic, addressing serial correlation in financial data.
problem Estimating Hurst exponent of log-volatility in financial time series with serial correlation.
method Proposes a random permutation procedure to remove serial correlation, using the Kolmogorov-Smirnov statistic for distribution-based estimation.
result Establishes the asymptotic variance of the estimator and reveals statistically significant hierarchy of roughness in volatility measures.
In this paper we address the problem of discovering a small set of frequent serial episodes from sequential data so as to adequately characterize or summarize the data. We discuss an algorithm based on the Minimum Description Length (MDL) principle and the algorithm is a slight modification of an earlier method, called…
mGRN improves multivariate time series prediction by managing marginal and joint memories.
problem Extracting dependencies in multivariate sequential data with strong serial and cross-sectional dependencies.
method Developed a novel recurrent network architecture, Memory-Gated Recurrent Networks (mGRN), with gates for marginal and joint memories.
result mGRN consistently outperforms state-of-the-art architectures on various public datasets.
Method predicts LFSM increments from past observations using codifference.
problem Forecasting LFSM increments from discrete-time observations.
method Uses codifference for serial dependence, with conditional expectation or projection for α>1 or α<2. result Method shows promising performance in forecasting volatilities, capturing kurtosis and serial dependence.
New algorithm for decentralized matching markets without prior preference rankings.
problem Decentralized two-sided matching markets without known preference rankings.
method Epoch-based CA-ETC algorithm for decentralized matching markets.
result Achieves player optimal expected regret of O(T_0 (K log T / T_0 Δ^2)^(1/γ) + T_0 (T / T_0)^γ).
A new algorithm reduces bias in estimating model parameters.
problem Efficient estimation of model parameters in non-linear state-space models.
method Parisian particle Gibbs (PPG) algorithm for bias reduction in online learning.
result Non-asymptotic bounds on bias and variance for PPG.
A new training method speeds up ResNet training by 3x with minimal accuracy loss.
problem Training ResNets is slow due to dependencies between modules.
method Serial-parallel hybrid training strategy with data augmentation and downsampling.
result Significant speedup over traditional methods with comparable accuracy.
We introduce two Python frameworks to train neural networks on large datasets: Blocks and Fuel. Blocks is based on Theano, a linear algebra compiler with CUDA-support. It facilitates the training of complex neural network models by providing parametrized Theano operations, attaching metadata to Theano's symbolic comput…
A method for noise reduction in functional time series using FPCA.
problem Noise contamination in functional time series.
method Extending FPCA to separate signal and noise components.
result Optimal projection minimizes mean integrated squared error.
The FSRM uses a multifractional process to capture price multifractality, revealing serial information for forecasting.
problem Capturing multifractal price dynamics for better forecasting.
method Developed a fractional stochastic regularity model based on multifractional processes and information theory.
result The serial information of the regularity process Ht can be theoretically determined, aiding in forecasting future price increments. Cluster jackknife improves inference for staggered DID methods.
problem Over-rejection of CSDID in small clusters or treated clusters.
method Cluster jackknife for CSDID inference.
result Cluster jackknife greatly improves inference for CSDID.
We extend conformal inference to general settings that allow for time series data. Our proposal is developed as a randomization method and accounts for potential serial dependence by including block structures in the permutation scheme. As a result, the proposed method retains the exact, model-free validity when the da…
New method for PKM inverse dynamics second derivatives efficiently.
problem Efficient computation of PKM inverse dynamics second derivatives.
method Recursive Lie-group formulation for serial robots adapted to PKM topology.
result Efficient computation of second time derivatives for PKM.