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.
Generative models need per-sample confidence scores to improve quality and stability.
Learning with few samples is a major challenge for parameter-rich models like deep networks. In contrast, people learn complex new concepts even from very few examples, suggesting that the sample complexity of learning can often be reduced. Many approaches to few-shot learning build on transferring a representation fro…
New method assesses individual training points' privacy risk without retraining.
New method for differentially private optimization with general Lipschitz conditions.
A new method improves training speed and robustness for deep learning models.
BatchTopK SAEs improve GPT-2 and Gemma activations with adjustable sparsity.
Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature importance scores, which identify features that are important for each individual input. …
This work focuses on a specific classification problem, where the information about a sample is not readily available, but has to be acquired for a cost, and there is a per-sample budget. Inspired by real-world use-cases, we analyze average and hard variations of a directly specified budget. We postulate the problem in…
Proposes a new method for uncertainty estimation in neural networks.
The parameters of temporal models, such as dynamic Bayesian networks, may be modelled in a Bayesian context as static or atemporal variables that influence transition probabilities at every time step. Particle filters fail for models that include such variables, while methods that use Gibbs sampling of parameter variab…
We present a new data-driven benchmark system to evaluate the performance of new MCMC samplers. Taking inspiration from the COCO benchmark in optimization, we view this task as having critical importance to machine learning and statistics given the rate at which new samplers are proposed. The common hand-crafted exampl…
New analysis shows how to balance privacy and accuracy in deep learning.
Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make them vulnerable to adversarial samples: inputs crafted by adversaries with the int…
High throughput genetic sequencing arrays with thousands of measurements per sample and a great amount of related censored clinical data have increased demanding need for better measurement specific model selection. In this paper we establish strong oracle properties of nonconcave penalized methods for nonpolynomial (N…
Recent progress in deep latent variable models has largely been driven by the development of flexible and scalable variational inference methods. Variational training of this type involves maximizing a lower bound on the log-likelihood, using samples from the variational posterior to compute the required gradients. Rec…
Paper proposes DP-SGD and DP-NSGD for differentially private non-convex optimization.
AMF-VI uses adaptive mixtures of flows for robust VI across diverse distributions.
A new EM algorithm improves inference from large datasets.
Enhanced reinforcement learning using ensemble methods.
New algorithm clusters LLM inputs efficiently with quality control.
Algorithm estimates principal eigenvector with adaptive sensing, improving over non-adaptive methods.
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…
Bayes-assisted confidence sequences improve efficiency for bounded means.
Continual learning based on data stream mining deals with ubiquitous sources of Big Data arriving at high-velocity and in real-time. Adaptive Random Forest ({\em ARF}) is a popular ensemble method used for continual learning due to its simplicity in combining adaptive leveraging bagging with fast random Hoeffding trees…
New method enhances neural network robustness against adversarial attacks.
A new method normalizes flow mixtures for better inference across different data types.
Single linear solve combines surface reconstruction and uncertainty quantification.
PTOPOFL uses topological descriptors to protect privacy in federated learning.
Paper detects Trojan neural networks with limited or no data.
We consider the problem of estimating the difference between two functional undirected graphical models with shared structures. In many applications, data are naturally regarded as high-dimensional random function vectors rather than multivariate scalars. For example, electroencephalography (EEG) data are more appropri…
Prediction intervals in supervised Machine Learning bound the region where the true outputs of new samples may fall. They are necessary in the task of separating reliable predictions of a trained model from near random guesses, minimizing the rate of False Positives, and other problem-specific tasks in applied Machine …
Nonlinear state-space models are powerful tools to describe dynamical structures in complex time series. In a streaming setting where data are processed one sample at a time, simultaneous inference of the state and its nonlinear dynamics has posed significant challenges in practice. We develop a novel online learning f…
Clapping reduces memory usage in distributed optimization by reusing data samples.
In population synthesis applications, when considering populations with many attributes, a fundamental problem is the estimation of rare combinations of feature attributes. Unsurprisingly, it is notably more difficult to reliably representthe sparser regions of such multivariate distributions and in particular combinat…
Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in many application settings matching subsequences (segments) instead of individual samples may bring in additional robustness to noise or local non-causal perturbations. Thi…
This paper investigates a multi-terminal source coding problem under a logarithmic loss fidelity which does not necessarily lead to an additive distortion measure. The problem is motivated by an extension of the Information Bottleneck method to a multi-source scenario where several encoders have to build cooperatively …
Transformer model removes noise from light curves efficiently.
While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training. Thus, for TX-Ray, we modify the established computer vision explainability principle…
Combines offline and online learning for identifying the best arm in bandits.
Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches. However, it is challenging to fully leverage different modalities due to practical challenges such as varying levels of noise and conflicts between modalities. Existing metho…
ViViT efficiently computes curvature for deep networks without approximations.
DP-RandP improves privacy-utility tradeoff in DP-SGD by learning priors from random processes.
Diffusion models outperform GANs in image synthesis quality.
We consider the problem of estimating the mean of a symmetric log-concave distribution under the constraint that only a single bit per sample from this distribution is available to the estimator. We study the mean squared error as a function of the sample size (and hence the number of bits). We consider three settings:…
When eliciting judgements from humans for an unknown quantity, one often has the choice of making direct-scoring (cardinal) or comparative (ordinal) measurements. In this paper we study the relative merits of either choice, providing empirical and theoretical guidelines for the selection of a measurement scheme. We pro…
When the cost of misclassifying a sample is high, it is useful to have an accurate estimate of uncertainty in the prediction for that sample. There are also multiple types of uncertainty which are best estimated in different ways, for example, uncertainty that is intrinsic to the training set may be well-handled by a B…
Logit regularization induces logit clustering, affecting classifier performance.
Paper proposes an unbiased optimization method for Bayesian experimental design.