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.
Gradient flow of ReLU networks converges in low-correlation high-dimensional data.
RAN model recognizes multiple activities from unlabeled sensor data.
An open problem in machine learning is whether flat minima generalize better and how to compute such minima efficiently. This is a very challenging problem. As a first step towards understanding this question we formalize it as an optimization problem with weakly interacting agents. We review appropriate background mat…
One approach to monitoring a dynamic system relies on decomposition of the system into weakly interacting subsystems. An earlier paper introduced a notion of weak interaction called separability, and showed that it leads to exact propagation of marginals for prediction. This paper addresses two questions left open by t…
In this work, we introduce a novel framework that employs cluster annotation to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, humans can also label clusters, producing a higher number of annotated samples wit…
Interactive machine learning with weak supervision and pre-trained embeddings.
Weakly supervised data are widespread and have attracted much attention. However, since label quality is often difficult to guarantee, sometimes the use of weakly supervised data will lead to unsatisfactory performance, i.e., performance degradation or poor performance gains. Moreover, it is usually not feasible to man…
Standard position for surfaces extended to weakly generalized alternating links.
This paper provides estimation and inference methods for a conditional average treatment effects (CATE) characterized by a high-dimensional parameter in both homogeneous cross-sectional and unit-heterogeneous dynamic panel data settings. In our leading example, we model CATE by interacting the base treatment variable w…
Paper tackles drowsy driving by learning from weakly labeled car acceleration data.
We study revenue optimization learning algorithms for repeated posted-price auctions where a seller interacts with a single strategic buyer that holds a fixed private valuation for a good and seeks to maximize his cumulative discounted surplus. For this setting, first, we propose a novel algorithm that never decreases …
Weakly supervised learning aims at coping with scarce labeled data. Previous weakly supervised studies typically assume that there is only one kind of weak supervision in data. In many applications, however, raw data usually contains more than one kind of weak supervision at the same time. For example, in user experien…
The scarcity of data annotated at the desired level of granularity is a recurring issue in many applications. Significant amounts of effort have been devoted to developing weakly supervised methods tailored to each individual setting, which are often carefully designed to take advantage of the particular properties of …
Paper tackles weakly supervised learning from similarity-confidence data.
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for training classifiers. In this paper, we present an attention-based convolutiona…
As machine learning algorithms become increasingly sophisticated to exploit subtle features of the data, they often become more dependent on simulations. This paper presents a new approach called weakly supervised classification in which class proportions are the only input into the machine learning algorithm. Using on…
Hierarchical text classification has many real-world applications. However, labeling a large number of documents is costly. In practice, we can use semi-supervised learning or weakly supervised learning (e.g., dataless classification) to reduce the labeling cost. In this paper, we propose a path cost-sensitive learning…
A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapt…
This paper considers a semi-supervised learning framework for weakly labeled polyphonic sound event detection problems for the DCASE 2019 challenge's task4 by combining both the tri-training and adversarial learning. The goal of the task4 is to detect onsets and offsets of multiple sound events in a single audio clip. …
Consider a classification problem where we do not have access to labels for individual training examples, but only have average labels over subpopulations. We give practical examples of this setup and show how such a classification task can usefully be analyzed as a weakly supervised clustering problem. We propose thre…
Weakly Einstein Kähler surfaces are characterized and classified.
TrustNet robustly learns noise patterns from trusted data to improve weakly-supervised classification.
The study examines weakly Einstein Lie groups and proves non-existence for certain types.
Classifies weakly Einstein submanifolds in space forms satisfying specific equalities.
Improves label propagation for weakly supervised learning.
The study explores weakly -Kähler hyperbolic manifolds.
Study shows genericity of singularities in spacetimes with weakly trapped submanifolds.
The study finds knots with specific surgeries that don't allow weak symplectic fillings.
GROOVE learns representations for weakly paired multimodal data.
Paper presents an audiovisual model to recognize sounds from weakly labeled video data.
This technical report is the union of two contributions to the discussion of the Read Paper "Riemann manifold Langevin and Hamiltonian Monte Carlo methods" by B. Calderhead and M. Girolami, presented in front of the Royal Statistical Society on October 13th 2010 and to appear in the Journal of the Royal Statistical Soc…
Paper proposes MTL for weakly labelled SED, improving performance with 2-step attention.
Study weakly weighted Einstein-Finsler metrics, showing specific curvature properties and characterizing them.
The paper provides examples of keen weakly reducible bridge spheres for links in b-bridge position.
Low-rank tensor decomposition and completion have attracted significant interest from academia given the ubiquity of tensor data. However, the low-rank structure is a global property, which will not be fulfilled when the data presents complex and weak dependencies given specific graph structures. One particular applica…
Subset selection improves weak supervision performance.
Minimal displacement set in weakly systolic complexes is systolic and embeds isometrically.
Improved object segmentation and tracking in video using optical flow and initial state conditioning.
Study on extended weakly symmetric spaces, classifying and providing an example.
Proposes a method to create predictive sets from partially labeled data.
New algorithm proves RL from partial obs is feasible.
There is a well developed theory of weakly symmetric Riemannian manifolds. Here it is shown that several results in the Riemannian case are also valid for weakly symmetric pseudo-Riemannian manifolds, but some require additional hypotheses. The topics discussed are homogeneity, geodesic completeness, the geodesic orbit…
Sharp rates found for learning with dependent data, avoiding sample size deflation.
Study assesses weakly-supervised methods for rare outcomes in medical records.
We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most datasets are "weakly labelled" having only a list of events present in each rec…
We describe an approach to Grammatical Error Correction (GEC) that is effective at making use of models trained on large amounts of weakly supervised bitext. We train the Transformer sequence-to-sequence model on 4B tokens of Wikipedia revisions and employ an iterative decoding strategy that is tailored to the loosely-…
Paper tackles robust deep learning from weakly dependent data with unbounded loss and input.
Classifies weakly Einstein hypersurfaces in spaces of constant curvature.