Vishnu Suresh Lokhande's research while affiliated with University of Wisconsin–Madison and other places

Publications (16)

Preprint
Full-text available
Pooling multiple neuroimaging datasets across institutions often enables improvements in statistical power when evaluating associations (e.g., between risk factors and disease outcomes) that may otherwise be too weak to detect. When there is only a {\em single} source of variability (e.g., different scanners), domain adaptation and matching the dis...
Preprint
Full-text available
Uncertainty estimation in deep models is essential in many real-world applications and has benefited from developments over the last several years. Recent evidence suggests that existing solutions dependent on simple Gaussian formulations may not be sufficient. However, moving to other distributions necessitates Monte Carlo (MC) sampling to estimat...
Preprint
Full-text available
Learning invariant representations is an important requirement when training machine learning models that are driven by spurious correlations in the datasets. These spurious correlations, between input samples and the target labels, wrongly direct the neural network predictions resulting in poor performance on certain groups, especially the minorit...
Article
Pooling datasets from multiple studies can significantly improve statistical power: larger sample sizes can enable the identification of otherwise weak disease‐specific patterns. When modern learning methods are utilized (e.g., for predicting progression to dementia), differences in data acquisition‐methods / scanner‐protocols can enable the model...
Article
Uncertainty estimation in deep models is essential in many real-world applications and has benefited from developments over the last several years. Recent evidence [Farquhar et al., 2020] suggests that existing solutions dependent on simple Gaussian formulations may not be sufficient. However, moving to other distributions necessitates Monte Carlo...
Preprint
Learning invariant representations is a critical first step in a number of machine learning tasks. A common approach corresponds to the so-called information bottleneck principle in which an application dependent function of mutual information is carefully chosen and optimized. Unfortunately, in practice, these functions are not suitable for optimi...
Article
Learning invariant representations is a critical first step in a number of machine learning tasks. A common approach corresponds to the so-called information bottleneck principle in which an application dependent function of mutual information is carefully chosen and optimized. Unfortunately, in practice, these functions are not suitable for optimi...
Chapter
Algorithmic decision making based on computer vision and machine learning methods continues to permeate our lives. But issues related to biases of these models and the extent to which they treat certain segments of the population unfairly, have led to legitimate concerns. There is agreement that because of biases in the datasets we present to the m...
Conference Paper
Rectified Linear Units (ReLUs) are among the most widely used activation function in a broad variety of tasks in vision. Recent theoretical results suggest that despite their excellent practical performance, in various cases, a substitution with basis expansions (e.g., polynomials) can yield significant benefits from both the optimization and gener...
Article
In this paper, we introduce a new optimization approach to Entity Resolution. Traditional approaches tackle entity resolution with hierarchical clustering, which does not benefit from a formal optimization formulation. In contrast, we model entity resolution as correlation-clustering, which we treat as a weighted set-packing problem and write as an...
Preprint
Algorithmic decision making based on computer vision and machine learning technologies continue to permeate our lives. But issues related to biases of these models and the extent to which they treat certain segments of the population unfairly, have led to concern in the general public. It is now accepted that because of biases in the datasets we pr...
Preprint
Modern computer vision (CV) is often based on convolutional neural networks (CNNs) that excel at hierarchical feature extraction. The previous generation of CV approaches was often based on conditional random fields (CRFs) that excel at modeling flexible higher order interactions. As their benefits are complementary they are often combined. However...
Preprint
We consider an active learning setting where the algorithm has access to a large pool of unlabeled data and a small pool of labeled data. In each iteration, the algorithm chooses few unlabeled data points and obtains their labels from an oracle. In this paper, we consider a probabilistic querying procedure to choose the points to be labeled. We pro...
Preprint
Rectified Linear Units (ReLUs) are among the most widely used activation function in a broad variety of tasks in vision. Recent theoretical results suggest that despite their excellent practical performance, in various cases, a substitution with basis expansions (e.g., polynomials) can yield significant benefits from both the optimization and gener...
Preprint
In this paper, we introduce a new optimization approach to Entity Resolution. Traditional approaches tackle entity resolution with hierarchical clustering, which does not benefit from a formal optimization formulation. In contrast, we model entity resolution as correlation-clustering, which we treat as a weighted set-packing problem and write as an...
Article
A number of results have recently demonstrated the benefits of incorporating various constraints when training deep architectures in vision and machine learning. The advantages range from guarantees for statistical generalization to better accuracy to compression. But support for general constraints within widely used libraries remains scarce and t...

Citations

... where w i is sampled from the Radial distribution (µ, σ) as described in equation (6) and p is the Likelihood of N (0, 1). Note that running an MC approximation for large M can lead to running out of memory in either a GPU or RAM, Nazarovs et al. (2021). To tackle this issue, we follow Nazarovs et al. (2021) and apply a graph parameterization for our Radial Spike and Slab distribution, allowing us to set M = 1000 without exhausting the memory. ...
... the model be invariant to the categorical variable denoting "site". While this is not a "solved" problem, this strategy has been successfully deployed based on results in invariant representation learning [3,5,34] (see Fig. 1). One may alternatively view this task via the lens of fairness -we want the model's performance to be fair with respect to the site variable. ...
... Fairness is becoming an important issue to consider in the design of learning algorithms. A common strategy to make an algorithm fair is to remove the influence of one/more protected attributes when training the models, see [28]. Most methods assume that the labels of protected attributes are known during training but this may not always be possible. ...
... There is an extensive variety of literature on semisupervised learning algorithms, especially after the boom of deep learning [41]. Among them, pseudo-label based methods [1,6,25,34,35,38] train a model on the existing labeled data and then use this model to generate pseudo-labels on the unlabeled data, which will later be used for additional training. Another emerging direction is to leverage selfsupervised learning algorithms such as RotNet [14], Jig-Saw [29], SimCLR [10], or MOCO [16] for unsupervised pretraining and then fine-tune with the limited labeled set [11,19]. ...
... Similar (yet different) classes of DOIs have been recently introduced in the literature. Flexible DOIs (Lokhande et al. 2020, Haghani et al. 2021 and their predecessors, varying DOIs and invariant DOIs , bound dual variables by exploiting the following observation: the change in the cost of a column incurred by removing an item from it is typically small and can often be efficiently, and provably, bounded. Thus, any primal solution to a set-covering (packing) problem in which items are overcovered can be projected to a lower cost solution where no items are overcovered. ...
... Wang et al., 2019;Hendriks et al., 2021). It has been reported that including prior information, particularly smoothness constraints, significantly improves the generalization capability of image processing networks (Ravi et al., 2019;Rosca et al., 2020). Because prior information helps improve searching efficiency by restricting the data space (Sirignano and Spiliopoulos, 2018), incorporating physical constraints can potentially improve the convergence as well as inference performance of neural networks. ...