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.
Develops a theory for equivariant networks with partial domain symmetry.
Critiques incorrect fixed point assertions in digital topology.
In this paper, we have proposed a brain signal classification method, which uses eigenvalues of the covariance matrix as features to classify images (topomaps) created from the brain signals. The signals are recorded during the answering of 2D and 3D questions. The system is used to classify the correct and incorrect a…
Corrects incorrect assertions about fixed points in digital topology.
Paper proposes methods to learn with multiple incorrect labels per example.
Incorrect fixed point assertions in digital topology are discussed.
Incorrect fixed point assertions in digital topology are discussed.
This paper presents an automated supervised method for Persian wordnet construction. Using a Persian corpus and a bi-lingual dictionary, the initial links between Persian words and Princeton WordNet synsets have been generated. These links will be discriminated later as correct or incorrect by employing seven features …
Given a binary prediction problem, which performance metric should the classifier optimize? We address this question by formalizing the problem of Metric Elicitation. The goal of metric elicitation is to discover the performance metric of a practitioner, which reflects her innate rewards (costs) for correct (incorrect)…
Paper presents a method to disrupt deep uncertainty estimation without affecting accuracy.
The paper corrects and improves previous assertions in digital topology.
Study shows AD for neural nets with machine-representable numbers can be incorrect.
Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world applications. One solution is to make supervised learning robust with imperfectl…
Paper finds previous work on submanifolds incorrect.
Fixed point assertions in digital topology are often incorrect or poorly stated.
The discriminative approach to classification using deep neural networks has become the de-facto standard in various fields. Complementing recent reservations about safety against adversarial examples, we show that conventional discriminative methods can easily be fooled to provide incorrect labels with very high confi…
Adaptive Misinformation defends against model stealing attacks by sending incorrect predictions for OOD queries.
We study the quantification of uncertainty of Convolutional Neural Networks (CNNs) based on gradient metrics. Unlike the classical softmax entropy, such metrics gather information from all layers of the CNN. We show for the EMNIST digits data set that for several such metrics we achieve the same meta classification acc…
Deep-MIL models fail to respect key MIL assumption, leading to incorrect learning.
Classifier chains are popular and effective method to tackle a multi-label classification problem. The aim of this paper is to study the asymptotic properties of the chain model in which the conditional probabilities are of the logistic form. In particular we find conditions on the number of labels and the distribution…
Fine-tuning neural networks to guarantee performance on specific examples can also introduce incorrect inputs.
The paper cleans label noise in supervised classification using Bernoulli sampling.
This paper was withdrawn as Lemma 2 is incorrect.
Proposes squentropy loss for improved classification accuracy and model calibration.
Withdrawn by the authors, the main theorem is incorrect
Cold posteriors in BNNs harm performance, likely due to incorrect likelihood.
Practically, we are often in the dilemma that the labeled data at hand are inadequate to train a reliable classifier, and more seriously, some of these labeled data may be mistakenly labeled due to the various human factors. Therefore, this paper proposes a novel semi-supervised learning paradigm that can handle both l…
Study on numerical reliability of AD for MaxPool in neural nets.
This paper is not ready for public consumption, as the last step (Figure 20) is incorrect.
A new approach to model rejection using density ratios.
In this work, a classification method for SSVEP-based BCI is proposed. The classification method uses features extracted by traditional SSVEP-based BCI methods and finds optimal discrimination thresholds for each feature to classify the targets. Optimising the thresholds is formalised as a maximisation task of a perfor…
We propose an approach to distinguish between correct and incorrect image classifications. Our approach can detect misclassifications which either occur ("natural errors"), or due to ("adversarial errors"), both in a single . Our appr…
Self-training improves neural sequence generation by correcting incorrect predictions.
Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to adversarial manipulations at testing time. Specifically, suppose we have a testing …
Section 1.3 was incorrect, and 2.1 will be removed from further submissions. A rewritten version will be posted in the future.
New framework for fair classification in adversarial settings with provable guarantees.
Incorrect parity-based descriptions of realizable Gauss diagrams found, but bipartite graphs provide a valid approach.
Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into making any desired incorrect classification, potentially with very high certainty. Se…
Machine learning models, especially based on deep architectures are used in everyday applications ranging from self driving cars to medical diagnostics. It has been shown that such models are dangerously susceptible to adversarial samples, indistinguishable from real samples to human eye, adversarial samples lead to in…
Efficient neural network ensembles improve image classification reliability and uncertainty quantification.
This study integrates cost-sensitive and causal classification methods.
Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even craft attacks by querying the model in black-box settings, where no information abou…
Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high confidence. To better understand this phenomenon, we study adversarially robust learning …
Paper improves image classification accuracy with a new Noise Modeling Network.
GIM uses neural networks with Gaussian distributions to detect out-of-distribution data.
Detecting and aggregating sentiments toward people, organizations, and events expressed in unstructured social media have become critical text mining operations. Early systems detected sentiments over whole passages, whereas more recently, target-specific sentiments have been of greater interest. In this paper, we pres…
Doubly robust self-training improves semi-supervised learning by balancing labeled and pseudo-labeled data.
Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate prediction uncertainty in a pre-trained neural network model. Our method estimates the tr…