Related papers: Boosting Certified $\ell_\infty$ Robustness with E…
Adversarial robustness is a key desirable property of neural networks. It has been empirically shown to be affected by their sizes, with larger networks being typically more robust. Recently, Bubeck and Sellke proved a lower bound on the…
Data auditing is a process to verify whether certain data have been removed from a trained model. A recently proposed method (Liu et al. 20) uses Kolmogorov-Smirnov (KS) distance for such data auditing. However, it fails under certain…
As deep neural networks can easily overfit noisy labels, robust training in the presence of noisy labels is becoming an important challenge in modern deep learning. While existing methods address this problem in various directions, they…
A memory efficient approach to ensembling neural networks is to share most weights among the ensembled models by means of a single reference network. We refer to this strategy as Embedded Ensembling (EE); its particular examples are…
Abstracting neural networks with constraints they impose on their inputs and outputs can be very useful in the analysis of neural network classifiers and to derive optimization-based algorithms for certification of stability and robustness…
AI inference at the edge is becoming increasingly common for low-latency services. However, edge environments are power- and resource-constrained, and susceptible to failures. Conventional failure resilience approaches, such as cloud…
Sensitivity-based robustness certification has emerged as a practical approach for certifying neural network robustness, including in settings that require verifiable guarantees. A key advantage of these methods is that certification is…
Machine learning is becoming ubiquitous. From finance to medicine, machine learning models are boosting decision-making processes and even outperforming humans in some tasks. This huge progress in terms of prediction quality does not…
Ensemble learning is a popular technique to improve the accuracy of machine learning models. It traditionally hinges on the rationale that aggregating multiple weak models can lead to better models with lower variance and hence higher…
This paper presents a framework for bounding the approximation error in imitation model predictive controllers utilizing neural networks. Leveraging the Lipschitz properties of these neural networks, we derive a bound that guides dataset…
Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts. The presence of spurious correlations in training datasets leads ERM-trained models to…
Ensemble learning is a technique where multiple component learners are combined through a protocol. We propose an Ensemble Neural Network (ENN) that uses the combined latent-feature space of multiple neural network classifiers to improve…
Sampling-based methods, e.g., Deep Ensembles and Bayesian Neural Nets have become promising approaches to improve the quality of uncertainty estimation and robust generalization. However, they suffer from a large model size and high latency…
We present an ensemble learning methodology that combines multiple existing robotic grasp synthesis algorithms and obtain a success rate that is significantly better than the individual algorithms. The methodology treats the grasping…
Most of the existing classification methods are aimed at minimization of empirical risk (through some simple point-based error measured with loss function) with added regularization. We propose to approach this problem in a more information…
Learning monotonic models with respect to a subset of the inputs is a desirable feature to effectively address the fairness, interpretability, and generalization issues in practice. Existing methods for learning monotonic neural networks…
Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations. Under the paradigm, the robustness of a classifier is aligned with the…
How to conduct teacher training for knowledge distillation is still an open problem. It has been widely observed that a best-performing teacher does not necessarily yield the best-performing student, suggesting a fundamental discrepancy…
Transferability of adversarial examples is a well-known property that endangers all classification models, even those that are only accessible through black-box queries. Prior work has shown that an ensemble of models is more resilient to…
Ensemble techniques are powerful approaches that combine several weak learners to build a stronger one. As a meta learning framework, ensemble techniques can easily be applied to many machine learning techniques. In this paper we propose a…