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.
Enhances physics-informed neural networks with adaptive sampling and weighting.
NS-GAN mode collapse due to sample weighting inversion, solved with MM-nsat.
Cross-validation under sample selection bias can, in principle, be done by importance-weighting the empirical risk. However, the importance-weighted risk estimator produces sub-optimal hyperparameter estimates in problem settings where large weights arise with high probability. We study its sampling variance as a funct…
New algorithm for training GNNs with learned weights.
Proposes a new method to improve regression models with reweighted samples.
Generative model initializes 2-layer network weights for small datasets.
New method reduces model bias and variance by adjusting training sample weights based on label uncertainty.
Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance. Sample re-weighting strategy is commonly used to alleviate this issue by designing a weighting function mapping from training loss to sample weight, and then iterating between weight recalculating an…
A new algorithm improves credit scoring accuracy for imbalanced data.
A training-free method for conditional sampling using flow matching.
Proposes a new method to adapt to covariate shifts in supervised learning.
The paper explores when to prioritize easy or hard samples in learning tasks.
Use of an autoencoder (AE) as a normal model is a state-of-the-art technique for unsupervised-anomaly detection in sounds (ADS). The AE is trained to minimize the sample mean of the anomaly score of normal sounds in a mini-batch. One problem with this approach is that the anomaly score of rare-normal sounds becomes hig…
We show that the skip-gram formulation of word2vec trained with negative sampling is equivalent to a weighted logistic PCA. This connection allows us to better understand the objective, compare it to other word embedding methods, and extend it to higher dimensional models.
Paper develops robust -NN algorithm for few samples.
Data analysis in high energy physics often deals with data samples consisting of a mixture of signal and background events. The sPlot technique is a common method to subtract the contribution of the background by assigning weights to events. Part of the weights are by design negative. Negative weights lead to the diver…
Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) since DNNs can easily overfit to the noisy labels. Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to train…
IWeS selects examples by entropy-based importance sampling for subset selection.
Paper proposes a new method for sampling from complex distributions.
Optimizes weights for better model performance in shifting data.
Low bit-width integer weights and activations are very important for efficient inference, especially with respect to lower power consumption. We propose Monte Carlo methods to quantize the weights and activations of pre-trained neural networks without any re-training. By performing importance sampling we obtain quantiz…
EWFM trains continuous flows with only energy evaluations, improving sample quality with fewer computations.
The Importance Weighted Auto Encoder (IWAE) objective has been shown to improve the training of generative models over the standard Variational Auto Encoder (VAE) objective. Here, we derive importance weighted extensions to AVB and AAE. These latent variable models use implicitly defined inference networks whose approx…
Losaw improves FI scores by decorrelating features in ML models.
In this paper, we explore techniques centered around periodic sampling of model weights that provide convergence improvements on gradient update methods (vanilla \acs{SGD}, Momentum, Adam) for a variety of vision problems (classification, detection, segmentation). Importantly, our algorithms provide better, faster and …
Unrolled neural networks emerged recently as an effective model for learning inverse maps appearing in image restoration tasks. However, their generalization risk (i.e., test mean-squared-error) and its link to network design and train sample size remains mysterious. Leveraging the Stein's Unbiased Risk Estimator (SURE…
Bayesian inference is known to provide a general framework for incorporating prior knowledge or specific properties into machine learning models via carefully choosing a prior distribution. In this work, we propose a new type of prior distributions for convolutional neural networks, deep weight prior (DWP), that exploi…
Adapts example weights to optimize black-box metrics.
One-Shot Neural architecture search (NAS) attracts broad attention recently due to its capacity to reduce the computational hours through weight sharing. However, extensive experiments on several recent works show that there is no positive correlation between the validation accuracy with inherited weights from the supe…
CUTS removes corruption from models without clean data, improving utility and security.
In this paper we propose a tensor-based nonlinear model for high-order data classification. The advantages of the proposed scheme are that (i) it significantly reduces the number of weight parameters, and hence of required training samples, and (ii) it retains the spatial structure of the input samples. The proposed mo…
Estimates how much samples inform neural network training and function.
Improves transfer learning by weighting importance based on test-over-training density.
Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in such scenarios. First, we propose a theoretically-principled label-distribution-awa…
Corrects distribution shift in target shift scenarios using importance weighting.
This paper improves volatility forecasting using dynamic subset selection in genetic programming.
Corrects sample selection bias in empirical risk minimization using importance sampling.
FairWASP optimizes training data to reduce disparities across subgroups.
Constraints improve deep neural network training by stabilizing and enhancing robustness.
Paper presents a method to summarize HMC samples for neural networks, providing meaningful uncertainty estimates.
The paper shows how training with synthetic data can lead to model improvement, not degradation, under certain conditions.
RSO uses random weight perturbations to train deep networks without gradients.
Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a networked sample where two or more training examples may share common features. We propose an efficient weighting method for learning from netw…
FAIRIF improves fairness in deep learning models without changing the model architecture.
Not all neural network architectures are created equal, some perform much better than others for certain tasks. But how important are the weight parameters of a neural network compared to its architecture? In this work, we question to what extent neural network architectures alone, without learning any weight parameter…
A learned generative model often produces biased statistics relative to the underlying data distribution. A standard technique to correct this bias is importance sampling, where samples from the model are weighted by the likelihood ratio under model and true distributions. When the likelihood ratio is unknown, it can b…
Our method upweights easy samples to mitigate forgetting in fine-tuning.
Recent work on mode connectivity in the loss landscape of deep neural networks has demonstrated that the locus of (sub-)optimal weight vectors lies on continuous paths. In this work, we train a neural network that serves as a hypernetwork, mapping a latent vector into high-performance (low-loss) weight vectors, general…