arXiv research

Self-directed learners can minimize mistakes in online classification.

Open problem seeks an online learning algorithm for binary classification.

Study the tradeoffs of bandit feedback in multiclass classification.

Gaptron algorithm reduces mistakes in online multiclass classification.

A deterministic apple tasting learner is developed, confirming a conjecture and providing tight bounds for mistake bounds.

A technique to quickly fix mistakes in neural networks.

We propose a voted dual averaging method for online classification problems with explicit regularization. This method employs the update rule of the regularized dual averaging (RDA) method, but only on the subsequence of training examples where a classification error is made. We derive a bound on the number of mistakes…

Study apple tasting feedback in online binary classification, providing new insights into minimax expected mistakes.

LEAK learns from mistakes to improve point cloud segmentation.

Study selective classification with limited feedback in online learning.

We study the problem of efficient online multiclass linear classification with bandit feedback, where all examples belong to one of $K$ classes and lie in the $d$-dimensional Euclidean space. Previous works have left open the challenge of designing efficient algorithms with finite mistake bounds when the data is linear…

Paper tackles noisy bandit feedback for multiclass classification.

We consider the online multiclass linear classification under the bandit feedback setting. Beygelzimer, Pál, Szörényi, Thiruvenkatachari, Wei, and Zhang [ICML'19] considered two notions of linear separability, weak and strong linear separability. When examples are strongly linearly separable with margin $γ$, they prese…

Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recen…

We introduce a conceptually simple and effective method to quantify the similarity between relations in knowledge bases. Specifically, our approach is based on the divergence between the conditional probability distributions over entity pairs. In this paper, these distributions are parameterized by a very simple neural…

Ahpatron improves online kernel learning with tighter mistake bounds.

Motivated by social balance theory, we develop a theory of link classification in signed networks using the correlation clustering index as measure of label regularity. We derive learning bounds in terms of correlation clustering within three fundamental transductive learning settings: online, batch and active. Our mai…

This note corrects one serious mistake and several smaller mistakes from arXiv:math/0502404. The main results of that paper are unchanged.

In this paper, we propose online algorithms for multiclass classification using partial labels. We propose two variants of Perceptron called Avg Perceptron and Max Perceptron to deal with the partial labeled data. We also propose Avg Pegasos and Max Pegasos, which are extensions of Pegasos algorithm. We also provide mi…

We retract the scalar curvature rigidity theorem as there is a mistake in the proof. We thank S. Montiel for pointing out the mistake.

For a number of reasons, computational intelligence and machine learning methods have been largely dismissed by the professional community. The reasons for this are numerous and varied, but inevitably amongst the reasons given is that the systems designed often do not perform as expected by their designers. The reasons…

Improved mistake bounds for transductive online learning.

Simplifies online learning with consistent oracle to fewer mistakes.

The paper studies how noisy labels impact decision-making in machine learning.

Class labels are often imperfectly observed, due to mistakes and to genuine ambiguity among classes. We propose a new semi-supervised deep generative model that explicitly models noisy labels, called the Mislabeled VAE (M-VAE). The M-VAE can perform better than existing deep generative models which do not account for l…

Develops a method to find costly high-confidence errors in black box models.

Study on tradeoffs between mistakes and ERM oracle calls in online and transductive learning.

SkewSize detects model biases by analyzing mistakes across subgroups.

Efficient algorithm for online learning with Massart noise achieves near-optimal mistake bound.

We classify all closed non-orientable P2-irreducible 3-manifolds with complexity up to 7, fixing two mistakes in our previous complexity-up-to-6 classification. We show that there is no such manifold with complexity less than 6, five with complexity 6 (the four flat ones and the filling of the Gieseking manifold, which…

Thompson Sampling is at most twice as bad as any other policy in Bayesian bandit models.

Corrected a mistake in a paper about minimal surfaces.

Using Jeff Holman's comments in Quantitative Finance to illustrate 4 critical errors students should learn to avoid: 1) Mistaking tails (4th moment) for volatility (2nd moment), 2) Missing Jensen's Inequality, 3) Analyzing the hedging wihout the underlying, 4) The necessity of a numeraire in finance.

Modified Perceptron handles strategic agents with limited position changes.

Despite being very effective in several classification tasks, Dynamic Ensemble Selection (DES) techniques can select classifiers that classify all samples in the region of competence as being from the same class. The Frienemy Indecision REgion DES (FIRE-DES) tackles this problem by pre-selecting classifiers that correc…

Paper analyzes mistake and generalization of MNIC classifiers.

We investigate the problem of active learning on a given tree whose nodes are assigned binary labels in an adversarial way. Inspired by recent results by Guillory and Bilmes, we characterize (up to constant factors) the optimal placement of queries so to minimize the mistakes made on the non-queried nodes. Our query se…

Research on predicting with lists of labels, characterizing learnability and providing algorithms.

Study on computable online learning with new conditions and complexities.

Study online learning of neural networks with margin condition.

Online learning makes sequence of decisions with partial data arrival where next movement of data is unknown. In this paper, we have presented a new technique as multiple times weight updating that update the weight iteratively forsame instance. The proposed technique analyzed with popular state-of-art algorithms from …

Efficient algorithm for self-directed learning of convex clusters on graphs.

Study on learning to predict dynamical systems without assuming their structure.

This note corrects the mistakes in the splicing formulas of the paper "Floer homology and splicing knot complements". The mistakes are the result of the incorrect assumption that for a knot $K$ inside a homology sphere $Y$, the involution on the knot Floer homology of $K$ which corresponds to moving the basepoints by o…

John Morgan and G,Tian pointed out a mistake in the concluding argument for our paper entitled "$C_1$ in [2] is zero", which was recently published in arXiv:1512.02098. We hereby acknowledge this mistake and correct the computation, leading to the conclusion that $C_1$ is non-zero and that their reference [2] does inde…

We present very efficient active learning algorithms for link classification in signed networks. Our algorithms are motivated by a stochastic model in which edge labels are obtained through perturbations of a initial sign assignment consistent with a two-clustering of the nodes. We provide a theoretical analysis within…

Traders underestimated risk-free rates, leading to poor investments.

This paper has been withdrawn by the authors, due a crucial mistake in Lemma 2