arXiv research

A minimalist approach improves LLM reasoning by filtering incorrect responses.

This paper improves loss functions for deep learning with noisy labels.

Study on numerical reliability of AD for MaxPool in neural nets.

Scaling algorithms improve joint training of deep energy-based models.

Critiques incorrect fixed point assertions in digital topology.

Corrects incorrect assertions about fixed points in digital topology.

Empirical study finds deep learning assumptions often incorrect.

Incorrect fixed point assertions in digital topology are discussed.

Incorrect fixed point assertions in digital topology are discussed.

The paper corrects and improves previous assertions in digital topology.

Study shows AD for neural nets with machine-representable numbers can be incorrect.

Develops a theory for equivariant networks with partial domain symmetry.

A new approach to make classifiers safer by allowing them to abstain from making decisions on adversarial inputs.

Paper finds previous work on submanifolds incorrect.

Fixed point assertions in digital topology are often incorrect or poorly stated.

This work tackles exploding inverses in INNs, revealing and mitigating their numerical non-invertibility.

Fine-tuning neural networks to guarantee performance on specific examples can also introduce incorrect inputs.

This paper was withdrawn as Lemma 2 is incorrect.

Withdrawn by the authors, the main theorem is incorrect

This paper is not ready for public consumption, as the last step (Figure 20) is incorrect.

Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make mistake. It always involves a defending side, usually a classifier, and an atta…

Section 1.3 was incorrect, and 2.1 will be removed from further submissions. A rewritten version will be posted in the future.

Incorrect parity-based descriptions of realizable Gauss diagrams found, but bipartite graphs provide a valid approach.

Paper proposes methods to learn with multiple incorrect labels per example.

A new method improves likelihood-free Bayesian inference by transforming summary statistics and using efficient Variational Bayes.

In finance, durations between successive transactions are usually modeled by the autoregressive conditional duration model based on a continuous distribution omitting zero values. Zero or close-to-zero durations can be caused by either split transactions or independent transactions. We propose a discrete model allowing…

Detects adversarial examples in deep speech recognition.

I show that Matsumoto conjectured inequality between relative length and Finsler length is false. The incorrectness of the claim is easily inferred from the geometry of the indicatrix.

This work improves motion planning for quadcopters by learning and reasoning about controller performance.

Improves estimation under model misspecification with fake features.

The Comment cond-mat/0503325 is built around two core statements, both of which are plainly incorrect.

New partial models correct for confounding effects in reinforcement learning.

The results in the recently posted manuscript arXiv:math/0405153v3 are incorrect. The correct version of the aimed results is not original. The preprint contains material from references that are not properly quoted.

Deep neural networks (DNNs) are vulnerable to maliciously generated adversarial examples. These examples are intentionally designed by making imperceptible perturbations and often mislead a DNN into making an incorrect prediction. This phenomenon means that there is significant risk in applying DNNs to safety-critical …

Several recent papers in digital topology have sought to obtain fixed point results by mimicking the use of tools from classical topology, such as complete metric spaces. We show that in many cases, researchers using these tools have derived conclusions that are incorrect, trivial, or limited.

This paper proposes a novel type of random forests called a denoising random forests that are robust against noises contained in test samples. Such noise-corrupted samples cause serious damage to the estimation performances of random forests, since unexpected child nodes are often selected and the leaf nodes that the i…

Corrects errors in previous work on linear elasticity calculations.

Paper warns of metric deformation in manifold learning, leading to incorrect answers.

We continue the work of [5] and [3], in which are considered papers in the literature that discuss fixed point assertions in digital topology. We discuss published assertions that are incorrect or incorrectly proven; that are severely limited or reduce to triviality under "usual" conditions; or that we improve upon.

Several recent papers in digital topology have sought to obtain fixed point results by mimicking the use of tools from classical topology, such as complete metric spaces and homotopy invariant fixed point theory. We show that in many cases, researchers using these tools have derived conclusions that are incorrect or tr…

This paper presents a novel approach for detection of liver abnormalities in an automated manner using ultrasound images. For this purpose, we have implemented a machine learning model that can not only generate labels (normal and abnormal) for a given ultrasound image but it can also detect when its prediction is like…

The Frölicher spectral sequence of a compact complex manifold $X$ measures the difference between Dolbeault cohomology and de Rham cohomology. We construct for $n\geq 2$ nilmanifolds with left-invariant complex structure $X_n$ such that the $n$-th differential $d_n$ does not vanish. This replaces an earlier incorrect e…

E-scores assess LLM outputs for correctness, addressing p-hacking issues.

We study Bayesian discriminative inference given a model family $p(c,\x, θ)$ that is assumed to contain all our prior information but still known to be incorrect. This falls in between "standard" Bayesian generative modeling and Bayesian regression, where the margin $p(\x,θ)$ is known to be uninformative about $p(c|\x,…

Deep-MIL models fail to respect key MIL assumption, leading to incorrect learning.

The Morse-Bott inequalities relate the topology of a closed manifold to the topology of the critical point set of a Morse-Bott function defined on it. The Morse-Bott inequalities are sometimes stated under incorrect orientation assumptions. We show that these assumptions are insufficient with an explicit counterexample…

This paper studies a stylized, yet natural, learning-to-rank problem and points out the critical incorrectness of a widely used nearest neighbor algorithm. We consider a model with $n$ agents (users) $\{x_i\}_{i \in [n]}$ and $m$ alternatives (items) $\{y_j\}_{j \in [m]}$, each of which is associated with a latent feat…

An active learner is given a hypothesis class, a large set of unlabeled examples and the ability to interactively query labels to an oracle of a subset of these examples; the goal of the learner is to learn a hypothesis in the class that fits the data well by making as few label queries as possible. This work addresses…