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.
Enhanced visual feature attribution via adaptive baseline weighting.
Paper uses GNN and conformal prediction for accurate edge weight prediction.
A new method uses nearest neighbors for importance weighting.
WiGS improves active learning for regression by dynamically selecting informative samples.
New method FedEx accelerates federated hyperparameter tuning.
Algorithm ranks assets in fluctuating markets.
Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In this work, in order to help ground the empirical results in this field, we propose new NAS baselines that build off the following observations: (i) …
This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabilities. To infer the parameters of DirVAE, we utilize the stochastic gradient method by approximating the Gamma distribution, which is a comp…
New metrics improve scRNA-seq perturbation modeling by reducing mode collapse.
Neural networks have achieved state of the art performance across a wide variety of machine learning tasks, often with large and computation-heavy models. Inducing sparseness as a way to reduce the memory and computation footprint of these models has seen significant research attention in recent years. In this paper, w…
With the development of deep neural networks, the size of network models becomes larger and larger. Model compression has become an urgent need for deploying these network models to mobile or embedded devices. Model quantization is a representative model compression technique. Although a lot of quantization methods hav…
We present a novel method of compression of deep Convolutional Neural Networks (CNNs) by weight sharing through a new representation of convolutional filters. The proposed method reduces the number of parameters of each convolutional layer by learning a 1D vector termed Filter Summary (FS). The convolutional filters ar…
New algorithm improves causal effect estimation for continuous treatments.
A new approach optimizes weights in DLP for better risk-adjusted performance.
We propose a new learning to rank algorithm, named Weighted Margin-Rank Batch loss (WMRB), to extend the popular Weighted Approximate-Rank Pairwise loss (WARP). WMRB uses a new rank estimator and an efficient batch training algorithm. The approach allows more accurate item rank approximation and explicit utilization of…
Algorithm learns which weights to share in deep multi-task learning.
Data augmentation is usually used by supervised learning approaches for offline writer identification, but such approaches require extra training data and potentially lead to overfitting errors. In this study, a semi-supervised feature learning pipeline was proposed to improve the performance of writer identification b…
A new metric, Weighted Regret, unifies FDR and power evaluation in online multiple testing.
The Matrix Factorization models, sometimes called the latent factor models, are a family of methods in the recommender system research area to (1) generate the latent factors for the users and the items and (2) predict users' ratings on items based on their latent factors. However, current Matrix Factorization models p…
EVCL combines VCL and EWC to prevent forgetting new tasks.
Optimizes pruning masks for neural networks using probabilistic fine-tuning and PAC-Bayes bounds.
Integrated gradients are widely employed to evaluate the contribution of input features in classification models because it satisfies the axioms for attribution of prediction. This method, however, requires an appropriate baseline for reliable determination of the contributions. We propose a compensated integrated grad…
Graph classification receives a great deal of attention from the non-Euclidean machine learning community. Recent advances in graph coarsening have enabled the training of deeper networks and produced new state-of-the-art results in many benchmark tasks. We examine how these architectures train and find that performanc…
New linear algorithms improve wSVMs for multiclass probability estimation.
Improves feature selection in high-dimensional data using LLM-generated weights.
Guarantees sparse recovery for neural networks with iterative hard thresholding.
This paper evaluates heuristics and hyperparameters in weight-sharing NAS methods.
Improved IV estimates by weighting on compliance reduces noise in treatment effect estimation.
A new method normalizes flow mixtures for better inference across different data types.
Adapts example weights to optimize black-box metrics.
Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e.g., the dialogue success and the dialogue length. In this work, we propose a structured method for finding a good balance between these components by searching for the optimal re…
LLMs outperform strong tabular baselines on industrial car retrofit prediction.
Human language is a rich multimodal signal consisting of spoken words, facial expressions, body gestures, and vocal intonations. Learning representations for these spoken utterances is a complex research problem due to the presence of multiple heterogeneous sources of information. Recent advances in multimodal learning…
Combining information from different sources is a common way to improve classification accuracy in Brain-Computer Interfacing (BCI). For instance, in small sample settings it is useful to integrate data from other subjects or sessions in order to improve the estimation quality of the spatial filters or the classifier. …
We introduce a DNN training technique that learns only a fraction of the full parameter set without incurring an accuracy penalty. To do this, our algorithm constrains the total number of weights updated during backpropagation to those with the highest total gradients. The remaining weights are not tracked, and their i…
Improves causal inference with observational data by balancing features and weights.
New method improves deep RL by combining emphatic weightings with replay data.
Independent Component Analysis (ICA) aims to find a coordinate system in which the components of the data are independent. In this paper we construct a new nonlinear ICA model, called WICA, which obtains better and more stable results than other algorithms. A crucial tool is given by a new efficient method of verifying…
TSC improves causal effect estimation in panel data.
Ricci-Filtration enhances retrieval-augmented generation rerankers for query-answer tasks by using discrete Ricci flow on graphs.
The impressive success of Generative Adversarial Networks (GANs) is often overshadowed by the difficulties in their training. Despite the continuous efforts and improvements, there are still open issues regarding their convergence properties. In this paper, we propose a simple training variation where suitable weights …
We analyse multimodal time-series data corresponding to weight, sleep and steps measurements. We focus on predicting whether a user will successfully achieve his/her weight objective. For this, we design several deep long short-term memory (LSTM) architectures, including a novel cross-modal LSTM (X-LSTM), and demonstra…
Sparse random networks reduce communication in federated learning.
Improves deep learning performance on noisy datasets using inverse-variance weighting.
Performance-critical machine learning models should be robust to input perturbations not seen during training. Adversarial training is a method for improving a model's robustness to some perturbations by including them in the training process, but this tends to exacerbate other vulnerabilities of the model. The adversa…
Unified framework for measuring concentration in weighted networks considering both weight distributions and network structure.
Study on Bayesian transformers finds issues with weight-space inference and prior specification.
Bayesian Quadrature improves ensembling for neural networks with dispersed likelihood peaks.