Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Manwani, Naresh"'
Automating end-to-end Exploratory Data Analysis (AutoEDA) is a challenging open problem, often tackled through Reinforcement Learning (RL) by learning to predict a sequence of analysis operations (FILTER, GROUP, etc). Defining rewards for each operat
Externí odkaz:
http://arxiv.org/abs/2410.11276
Robustness towards adversarial attacks is a vital property for classifiers in several applications such as autonomous driving, medical diagnosis, etc. Also, in such scenarios, where the cost of misclassification is very high, knowing when to abstain
Externí odkaz:
http://arxiv.org/abs/2410.10736
Partial label learning (PLL) is a weakly-supervised learning paradigm where each training instance is paired with a set of candidate labels (partial label), one of which is the true label. Noisy PLL (NPLL) relaxes this constraint by allowing some par
Externí odkaz:
http://arxiv.org/abs/2402.04835
This paper presents a robust approach for learning from noisy pairwise comparisons. We propose sufficient conditions on the loss function under which the risk minimization framework becomes robust to noise in the pairwise similar dissimilar data. Our
Externí odkaz:
http://arxiv.org/abs/2303.02341
Autor:
Manwani, Naresh, Agarwal, Mudit
In this paper, we present online algorithm called {\it Delaytron} for learning multi class classifiers using delayed bandit feedbacks. The sequence of feedback delays $\{d_t\}_{t=1}^T$ is unknown to the algorithm. At the $t$-th round, the algorithm o
Externí odkaz:
http://arxiv.org/abs/2205.08234
In this paper, we propose deep architectures for learning instance specific abstain (reject option) binary classifiers. The proposed approach uses double sigmoid loss function as described by Kulin Shah and Naresh Manwani in ("Online Active Learning
Externí odkaz:
http://arxiv.org/abs/2107.03090
Autor:
Batra, Gaurav, Manwani, Naresh
This paper introduces a new online learning framework for multiclass classification called learning with diluted bandit feedback. At every time step, the algorithm predicts a candidate label set instead of a single label for the observed example. It
Externí odkaz:
http://arxiv.org/abs/2105.08093
In this paper, we investigate a constrained formulation of neural networks where the output is a convex function of the input. We show that the convexity constraints can be enforced on both fully connected and convolutional layers, making them applic
Externí odkaz:
http://arxiv.org/abs/2006.05103
Autor:
Agarwal, Mudit, Manwani, Naresh
Publikováno v:
Pacific-Asia Conference on Knowledge Discovery and Data Mining,2021
This paper addresses the problem of multiclass classification with corrupted or noisy bandit feedback. In this setting, the learner may not receive true feedback. Instead, it receives feedback that has been flipped with some non-zero probability. We
Externí odkaz:
http://arxiv.org/abs/2006.03545
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
Externí odkaz:
http://arxiv.org/abs/1912.11367