We present unexpected findings from a large-scale benchmark study evaluating Conditional Average Treatment Effect (CATE) estimation algorithms. By running 16 modern CATE models across 43,200 datasets, we find that: (a) 62\% of CATE estimates have a higher Mean Squared Error (MSE) than a trivial zero-effect predictor, rendering them ineffective; (b) in datasets with at least one useful CATE estimate, 80\% still have higher MSE than a constant-effect model; and (c) Orthogonality-based models outperform other models only 30\% of the time, despite widespread optimism about their performance. These findings expose significant limitations in current CATE models and suggest ample opportunities for further research. Our findings stem from a novel application of \textit{observational sampling}, originally developed to evaluate Average Treatment Effect (ATE) estimates from observational methods with experiment data. To adapt observational sampling for CATE evaluation, we introduce a statistical parameter, $Q$, equal to MSE minus a constant and preserves the ranking of models by their MSE. We then derive a family of sample statistics, collectively called $\hat{Q}$, that can be computed from real-world data. We prove that $\hat{Q}$ is a consistent estimator of $Q$ under mild technical conditions. When used in observational sampling, $\hat{Q}$ is unbiased and asymptotically selects the model with the smallest MSE. To ensure the benchmark reflects real-world heterogeneity, we handpick datasets where outcomes come from field rather than simulation. By combining the new observational sampling method, new statistics, and real-world datasets, the benchmark provides a unique perspective on CATE estimator performance and uncover gaps in capturing real-world heterogeneity.

In this work, we propose a mean-squared error-based risk that enables the comparison and optimization of estimators of squared calibration errors in practical settings. Improving the calibration of classifiers is crucial for enhancing the trustworthiness and interpretability of machine learning models, especially in sensitive decision-making scenarios. Although various calibration (error) estimators exist in the current literature, there is a lack of guidance on selecting the appropriate estimator and tuning its hyperparameters. By leveraging the bilinear structure of squared calibration errors, we reformulate calibration estimation as a regression problem with independent and identically distributed (i.i.d.) input pairs. This reformulation allows us to quantify the performance of different estimators even for the most challenging calibration criterion, known as canonical calibration. Our approach advocates for a training-validation-testing pipeline when estimating a calibration error on an evaluation dataset. We demonstrate the effectiveness of our pipeline by optimizing existing calibration estimators and comparing them with novel kernel ridge regression-based estimators on standard image classification tasks.

Deep InfoMax (DIM) is a well-established method for self-supervised representation learning (SSRL) based on maximization of the mutual information between the input and the output of a deep neural network encoder. Despite the DIM and contrastive SSRL in general being well-explored, the task of learning representations conforming to a specific distribution (i.e., distribution matching, DM) is still under-addressed. Motivated by the importance of DM to several downstream tasks (including generative modeling, disentanglement, outliers detection and other), we enhance DIM to enable automatic matching of learned representations to a selected prior distribution. To achieve this, we propose injecting an independent noise into the normalized outputs of the encoder, while keeping the same InfoMax training objective. We show that such modification allows for learning uniformly and normally distributed representations, as well as representations of other absolutely continuous distributions. Our approach is tested on various downstream tasks. The results indicate a moderate trade-off between the performance on the downstream tasks and quality of DM.

Recent works have shown theoretically and empirically that redundant data dimensions are a source of adversarial vulnerability. However, the inverse doesn't seem to hold in practice; employing dimension-reduction techniques doesn't exhibit robustness as expected. In this work, we consider classification tasks and characterize the data distribution as a low-dimensional manifold, with high/low variance features defining the on/off manifold direction. We argue that clean training experiences poor convergence in the off-manifold direction caused by the ill-conditioning in widely used first-order optimizers like gradient descent. The poor convergence then acts as a source of adversarial vulnerability when the dataset is inseparable in the on-manifold direction. We provide theoretical results for logistic regression and a 2-layer linear network on the considered data distribution. Furthermore, we advocate using second-order methods that are immune to ill-conditioning and lead to better robustness. We perform experiments and exhibit tremendous robustness improvements in clean training through long training and the employment of second-order methods, corroborating our framework. Additionally, we find the inclusion of batch-norm layers hinders such robustness gains. We attribute this to differing implicit biases between traditional and batch-normalized neural networks.

The effect of relative entropy asymmetry is analyzed in the context of empirical risk minimization (ERM) with relative entropy regularization (ERM-RER). Two regularizations are considered: $(a)$ the relative entropy of the measure to be optimized with respect to a reference measure (Type-I ERM-RER); or $(b)$ the relative entropy of the reference measure with respect to the measure to be optimized (Type-II ERM-RER). The main result is the characterization of the solution to the Type-II ERM-RER problem and its key properties. By comparing the well-understood Type-I ERM-RER with Type-II ERM-RER, the effects of entropy asymmetry are highlighted. The analysis shows that in both cases, regularization by relative entropy forces the solution's support to collapse into the support of the reference measure, introducing a strong inductive bias that can overshadow the evidence provided by the training data. Finally, it is shown that Type-II regularization is equivalent to Type-I regularization with an appropriate transformation of the empirical risk function.

Faithfulness is arguably the most critical metric to assess the reliability of explainable AI. In NLP, current methods for faithfulness evaluation are fraught with discrepancies and biases, often failing to capture the true reasoning of models. We introduce Adversarial Sensitivity as a novel approach to faithfulness evaluation, focusing on the explainer's response when the model is under adversarial attack. Our method accounts for the faithfulness of explainers by capturing sensitivity to adversarial input changes. This work addresses significant limitations in existing evaluation techniques, and furthermore, quantifies faithfulness from a crucial yet underexplored paradigm.

The paper combines ES and SGD in a complementary way, not viewing as an alternative to each other. More intuitively, in the course of optimization, the author proposes to use evolutionary strategy to make optimiser adjust at different sections (geometry) of optimisation path. Since the geometry of the loss surface can differ drastically at different locations, it is reasonable to use different gradient based optimisers with different hyper parameters at different locations. Then the main question becomes how to choose a proper optimiser at different locations. The paper proposes ES for that.

The authors develop prior networks, an approach to identifying misclassification on in and out of distribution examples. The work largely builds upon Malinin et al, 2017, adapting their method to the Dirichlet case. The experiments are simple but lack controls and may be too simple to validate the method. Overall: Quality: There do not appear to be any obvious errors. There is no model uncertainty in this paper as a dirac is used for the model prior, so why spend time talkimg about it?

This paper proposes doing dropout in the output softmax layer during supervised training of neural net classifiers. The dropout probabilities are adapted per example. The probabilities are computed as a function of the penultimate layer of the classifier. So that layer is used to compute both: the logits, and the gating for those logits. This model combines ideas from adaptive dropout (Ba and Frey NIPS'13) and variational dropout (Kingma et al). The key problem being solved is how to do inference to get the optimal dropout probabilities.

We study the implicit regularization imposed by gradient descent for learning multi-layer homogeneous functions including feed-forward fully connected and convolutional deep neural networks with linear, ReLU or Leaky ReLU activation. We rigorously prove that gradient flow (i.e. This result implies that if the weights are initially small, gradient flow automatically balances the magnitudes of all layers. Using a discretization argument, we analyze gradient descent with positive step size for the non-convex low-rank asymmetric matrix factorization problem without any regularization. Inspired by our findings for gradient flow, we prove that gradient descent with step sizes \eta_t O(t { (1/2 \delta)}) (0 \delta\le1/2) automatically balances two low-rank factors and converges to a bounded global optimum.