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.
QC-ST and CoCo methods correct batch effects in metabolomics data.
Improved TD learning reduces batch sampling error.
Anytime-valid confirmation of label-shift corrections
Recently, a lot of effort has been paid to the efficient computation of Kriging predictors when observations are assimilated sequentially. In particular, Kriging update formulae enabling significant computational savings were derived in Barnes and Watson (1992), Gao et al. (1996), and Emery (2009). Taking advantage of …
The study analyzes batched methods for early stopping in stochastic multi-armed bandits.
Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD): the variance in predicted probability of the correct class across iterations of …
A new method improves data representation for diverse tasks.
Given a finite set of unknown distributions or arms that can be sampled, we consider the problem of identifying the one with the maximum mean using a -correct algorithm (an adaptive, sequential algorithm that restricts the probability of error to a specified ) that has minimum sample complexity. Lower bounds for …
We make policy optimization algorithms batch size-invariant by decoupling proximal and behavior policies.
Geometric approach finds correspondences between different conditions.
Two new algorithms improve Q* approximation in batch RL with linear error propagation.
Adaptive Langevin dynamics reduces bias in Bayesian inference with mini-batching.
In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data parallelism seem to differ from domain to domain, ranging from batches of tens of thousands in ImageNet to …
Many biological data analysis processes like Cytometry or Next Generation Sequencing (NGS) produce massive amounts of data which needs to be processed in batches for down-stream analysis. Such datasets are prone to technical variations due to difference in handling the batches possibly at different times, by different …
Paper proposes an efficient method for bounding box annotation in object detection.
Introduce a variance-weighted batch distribution for diverse sampling in diffusion models.
A new method for batch prediction sets in classification problems.
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, largely depends on accuracy and correctness of these priors. PAC-Bayesian methods overcome this problem by providing bounds that hold regardless …
New SGD algorithm finds critical points faster with second-order corrections.
Bias correction improves language model training performance.
We propose a novel framework for combining datasets via alignment of their intrinsic geometry. This alignment can be used to fuse data originating from disparate modalities, or to correct batch effects while preserving intrinsic data structure. Importantly, we do not assume any pointwise correspondence between datasets…
WEINCE improves contrastive learning by correcting softmax biases.
DAIS improves AIS for differentiable marginal likelihood estimation.
AMAGOLD improves stochastic gradient MCMC by infrequent Metropolis-Hastings corrections.
In this study, we consider classification problems based on neural networks in data-imbalanced environment. Learning from an imbalanced data set is one of the most important and practical problems in the field of machine learning. A weighted loss function based on cost-sensitive approach is a well-known effective metho…
Estimates stationary distribution from batch transitions without access to the underlying process.
In this paper, we present NESTA, a specialized Neural engine that significantly accelerates the computation of convolution layers in a deep convolutional neural network, while reducing the computational energy. NESTA reformats Convolutions into batches and uses a hierarchy of Hamming Weight Compressors to …
Stein shrinkage improves BN robustness against adversarial attacks.
This work tackles sequential data learning challenges by improving neural network robustness to non-iid distribution shifts.
New method for constructing confidence intervals for time series data.
Bayesian method corrects bias in imbalanced datasets.
We study the dynamics of the `batch' minority game with market-impact correction using generating functional techniques to carry out the quenched disorder average. We find that the assumption of weak long-term memory, which one usually makes in order to calculate ergodic stationary states, breaks down when the persiste…
In this study, classification problems based on feedforward neural networks in a data-imbalanced environment are considered. Learning from an imbalanced dataset is one of the most important practical problems in the field of machine learning. A weighted loss function (WLF) based on a cost-sensitive approach is a well-k…
Improved method finds second-order stationary points privately with better efficiency.
In many real-world AD applications including computer security and fraud prevention, the anomaly detector must be configurable by the human analyst to minimize the effort on false positives. One important way to configure the detector is by providing true labels (nominal or anomaly) for a few instances. Recent work on …
Study improves BN TTA under distribution shift using higher-order asymptotics.
BEMA reduces bias in EMA, leading to faster convergence and better performance.
Data parallelism has become the de facto standard for training Deep Neural Network on multiple processing units. In this work we propose DC-S3GD, a decentralized (without Parameter Server) stale-synchronous version of the Delay-Compensated Asynchronous Stochastic Gradient Descent (DC-ASGD) algorithm. In our approach, w…
We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and network architecture. They simply amount to at most a matrix inversion and mult…
Study aggregation of statistical evidence under unknown dependence using group-invariance.
Several recent trends in machine learning theory and practice, from the design of state-of-the-art Gaussian Process to the convergence analysis of deep neural nets (DNNs) under stochastic gradient descent (SGD), have found it fruitful to study wide random neural networks. Central to these approaches are certain scaling…
This paper describes some applications of an incremental implementation of the principal component analysis (PCA). The algorithm updates the transformation coefficients matrix on-line for each new sample, without the need to keep all the samples in memory. The algorithm is formally equivalent to the usual batch version…
We present a novel Metropolis-Hastings method for large datasets that uses small expected-size minibatches of data. Previous work on reducing the cost of Metropolis-Hastings tests yield variable data consumed per sample, with only constant factor reductions versus using the full dataset for each sample. Here we present…
Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks. Its tendency to improve accuracy and speed up training have established BN as a favorite technique in deep learning. Yet, despite its enormous success, there remains little consensus on the exact reason and …
Data preprocessing techniques are devoted to correct or alleviate errors in data. Discretization and feature selection are two of the most extended data preprocessing techniques. Although we can find many proposals for static Big Data preprocessing, there is little research devoted to the continuous Big Data problem. A…
New algorithm speeds up MCMC for deep learning models.
New test detects independence in streaming data, adapting to data complexity.
Revisits online Laplace methods for neural networks, showing they are sound under certain conditions.