Contrastive learning involves learning representations via a loss function that encourages each (unlabeled) sample to be far from other samples, but close to its own *augmentation*. In this paper, we aim to understand why this simple idea performs remarkably well, by theoretically analyzing it for a simple, natural problem setting: dimensionality reduction in Gaussian Mixture Models (GMMs). Note that the standard GMM setup lacks the concept of augmentations. We study an intuitive extension: we define the pair of data sample and its augmentation as a coupled random draw from the GMM such that the marginal over the "noisy" augmentation is *biased* towards the component of the data sample. For this setup, we show that vanilla contrastive loss, e.g., InfoNCE, is able to find the *optimal* lower-dimensional subspace even when the Gaussian components are non-isotropic. In particular, we show that InfoNCE can match the performance of a fully supervised algorithm, e.g., LDA, (where each data point is labeled with the mixture component it comes from) even when the augmentations are "noisy". We further extend our setup to the multi-modal case, and develop a GMM-like setting to study the contrastive CLIP loss. We corroborate our theoretical with real-data experiments on CIFAR100; representations learned by InfoNCE loss match the performance of LDA on clustering metrics.

It is well known that selecting samples with large losses/gradients can significantly reduce the number of training steps. However, the selection overhead is often too high to yield any meaningful gains in terms of overall training time. In this work, we focus on the greedy approach of selecting samples with large approximate losses instead of exact losses in order to reduce the selection overhead. For smooth convex losses, we show that such a greedy strategy can converge to a constant factor of the minimum value of the average loss in fewer iterations than the standard approach of random selection. We also theoretically quantify the effect of the approximation level. We then develop SIFT which uses early exiting to obtain approximate losses with an intermediate layer’s representations for sample selection. We evaluate SIFT on the task of training a 110M parameter 12 layer BERT base model, and show significant gains (in terms of training hours and number of backpropagation steps) without any optimized implementation over vanilla training. For e.g., to reach 64% validation accuracy, SIFT with exit at the first layer takes $\sim$ 43 hours compared to $\sim$ 57 hours of vanilla training.

To address the problem of NLP classifiers learning spurious correlations between training features and target labels, a common approach is to make the model's predictions invariant to these features.However, this can be counterproductive when the features have a non-zero causal effect on the target label and thus are important for prediction.Therefore, using methods from the causal inference literature, we propose an algorithm to regularize the learnt effect of the features on the model's prediction to the estimated effect of feature on label.This results in an automated augmentation method that leverages the estimated effect of a feature to appropriately change the labels for new augmented inputs.On toxicity and IMDB review datasets, the proposed algorithm minimises spurious correlations and improves the minority group (i.e., samples breaking spurious correlations) accuracy, while also improving the total accuracy compared to standard training.1

We present DeepMVI, a deep learning method for missing value imputation in multidimensional time-series datasets. Missing values are commonplace in decision support platforms that aggregate data over long time stretches from disparate sources, whereas reliable data analytics calls for careful handling of missing data. One strategy is imputing the missing values, and a wide variety of algorithms exist spanning simple interpolation, matrix factorization methods like SVD, statistical models like Kalman filters, and recent deep learning methods. We show that often these provide worse results on aggregate analytics compared to just excluding the missing data. DeepMVI expresses the distribution of each missing value conditioned on coarse and fine-grained signals along a time series, and signals from correlated series at the same time. Instead of resorting to linearity assumptions of conventional matrix factorization methods, DeepMVI harnesses a flexible deep network to extract and combine these signals in an end-to-end manner. To prevent over-fitting with high-capacity neural networks, we design a robust parameter training with labeled data created using synthetic missing blocks around available indices. Our neural network uses a modular design with a novel temporal transformer with convolutional features, and kernel regression with learned embeddings. Experiments across ten real datasets, five different missing scenarios, comparing seven conventional and three deep learning methods show that DeepMVI is significantly more accurate, reducing error by more than 50% in more than half the cases, compared to the best existing method. Although slower than simpler matrix factorization methods, we justify the increased time overheads by showing that DeepMVI provides significantly more accurate imputation that finally impacts quality of downstream analytics.