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.
Ablation studies show BCF model's propensity score is not essential for treatment effect estimation.
Study ablated data augmentation techniques and their mathematical equivalence to penalties.
ABC method analyzes diffusion model dependence without retraining.
In microsurgery, lasers have emerged as precise tools for bone ablation. A challenge is automatic control of laser bone ablation with 4D optical coherence tomography (OCT). OCT as high resolution imaging modality provides volumetric images of tissue and foresees information of bone position and orientation (pose) as we…
Given a model that predicts a target from a vector of input features , we seek to measure the importance of each feature with respect to the model's ability to make a good prediction. To this end, we consider how (on average) some measure of goodness or badness of prediction (wh…
TSFMs show redundant components in layers, affecting their performance.
In this work, we investigate the use of three information-theoretic quantities -- entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler divergence -- to understand and study the behavior of already trained fully-connected feed-forward neural networks. We analyze …
Predicts stock volatility using Twitter data and random forests.
ECP optimizes expensive functions without knowing Lipschitz constant.
Hydra boosts efficiency for long-context reasoning in resource-constrained settings.
Deep learning improves forensic matching of casings.
This paper presents a supervised learning algorithm, namely, the Synaptic Efficacy Function with Meta-neuron based learning algorithm (SEF-M) for a spiking neural network with a time-varying weight model. For a given pattern, SEF-M uses the learning algorithm derived from meta-neuron based learning algorithm to determi…
Long Short Term Memory Fully Convolutional Neural Networks (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN) have shown to achieve state-of-the-art performance on the task of classifying time series signals on the old University of California-Riverside (UCR) time series repository. However, there has been no study on why L…
Paper proposes forecast-necessity testing for accurate causal interpretation in nonlinear time-series models.
Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smoothing: the robust classification is a consensus of base classifications on randomly noised samples where the noise is additive. In this pap…
A novel gradient boosting framework is proposed where shallow neural networks are employed as ``weak learners''. General loss functions are considered under this unified framework with specific examples presented for classification, regression, and learning to rank. A fully corrective step is incorporated to remedy the…
In this paper we study the problem of acoustic scene classification, i.e., categorization of audio sequences into mutually exclusive classes based on their spectral content. We describe the methods and results discovered during a competition organized in the context of a graduate machine learning course; both by the st…
Review of integrating Bayesian methods with neural network-based MPC.
CIT and CIF improve feature selection for downstream prediction.
INFERS PDEs from data samples using learned context.
New dataset tests mental rotation from single images, improving model understanding of 3D scenes.
Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimization problem. In this paper, we give a formalization of this shared pattern, which we call GIMLI, prove its general requirements, and derive…
Learning the preferences of a human improves the quality of the interaction with the human. The number of queries available to learn preferences maybe limited especially when interacting with a human, and so active learning is a must. One approach to active learning is to use uncertainty sampling to decide the informat…
In this work, we introduce a new method for imitation learning from video demonstrations. Our method, Relational Mimic (RM), improves on previous visual imitation learning methods by combining generative adversarial networks and relational learning. RM is flexible and can be used in conjunction with other recent advanc…
Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time by leveraging proxy models, leading to architectures with competitive performance compared to those with hand-crafted designs. In this pape…
Aims to create a world model without baggage, achieving good performance.
Enhances neural forecasting for hierarchically organized time series data.
The problem of attributing a deep network's prediction to its \emph{input/base} features is well-studied. We introduce the notion of \emph{conductance} to extend the notion of attribution to the understanding the importance of \emph{hidden} units. Informally, the conductance of a hidden unit of a deep network is the \e…
Bayesian optimization with preference learning using monotonic neural networks.
New mechanisms from primate vision improve neural network robustness.
Sparse point observations can provide useful local constraints, but their benefit for radar-like fields depends on the training loss, uncertainty representation, and how observation support is encoded in the model.
We review some of the latest approaches to analysing cardiac electrophysiology data using machine learning and predictive modelling. Cardiac arrhythmias, particularly atrial fibrillation, are a major global healthcare challenge. Treatment is often through catheter ablation, which involves the targeted localized destruc…
Towards the challenging problem of semi-supervised node classification, there have been extensive studies. As a frontier, Graph Neural Networks (GNNs) have aroused great interest recently, which update the representation of each node by aggregating information of its neighbors. However, most GNNs have shallow layers wi…
Optimizes neural networks by removing unnecessary layers, improving performance and speed.
Community detection is a fundamental problem in machine learning. While deep learning has shown great promise in many graphrelated tasks, developing neural models for community detection has received surprisingly little attention. The few existing approaches focus on detecting disjoint communities, even though communit…
MixBoost generates synthetic instances to balance imbalanced datasets.
Capsule networks improve with dynamic routing using Wasserstein objective.
Method generates anatomically-controllable medical images with segmentation guidance.
Double descent phenomenon explained in simple terms.
Sparse reward is one of the biggest challenges in reinforcement learning (RL). In this paper, we propose a novel method called Generative Exploration and Exploitation (GENE) to overcome sparse reward. GENE automatically generates start states to encourage the agent to explore the environment and to exploit received rew…
IGSD separates task-specific content channels in transformer components by comparing activation replacement with zero ablation.
Study on rapid policy changes in reinforcement learning.
VAR-GPs solve continual learning by updating posteriors sequentially.
Colored noise improves neural network robustness against adversarial attacks.
EXAGREE selects a stakeholder-aligned model to reduce conflicting explanations in machine learning.
Recent advances in deep learning-based object detection techniques have revolutionized their applicability in several fields. However, since these methods rely on unwieldy and large amounts of data, a common practice is to download models pre-trained on standard datasets and fine-tune them for specific application doma…
Embedding-based Knowledge Base Completion models have so far mostly combined distributed representations of individual entities or relations to compute truth scores of missing links. Facts can however also be represented using pairwise embeddings, i.e. embeddings for pairs of entities and relations. In this paper we ex…
Researchers propose better probabilistic models for deep learning.