Related papers: Class Distribution Shifts in Zero-Shot Learning: L…

We consider training machine learning models that are fair in the sense that their performance is invariant under certain sensitive perturbations to the inputs. For example, the performance of a resume screening system should be invariant…

Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful…

Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned policy can become robust…

Most machine learning models operate under the assumption that the training, testing and deployment data is independent and identically distributed (i.i.d.). This assumption doesn't generally hold true in a natural setting. Usually, the…

Distributionally Robust Supervised Learning (DRSL) is necessary for building reliable machine learning systems. When machine learning is deployed in the real world, its performance can be significantly degraded because test data may follow…

We present a generative framework for generalized zero-shot learning where the training and test classes are not necessarily disjoint. Built upon a variational autoencoder based architecture, consisting of a probabilistic encoder and a…

In Generalized Zero-Shot Learning (GZSL), unseen categories (for which no visual data are available at training time) can be predicted by leveraging their class embeddings (e.g., a list of attributes describing them) together with a…

A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and…

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes…

Zero-shot Learning (ZSL) aims to enable image classifiers to recognize images from unseen classes that were not included during training. Unlike traditional supervised classification, ZSL typically relies on learning a mapping from visual…

The Zero-Shot Learning (ZSL) task attempts to learn concepts without any labeled data. Unlike traditional classification/detection tasks, the evaluation environment is provided unseen classes never encountered during training. As such, it…

Learning accurate models of the physical world is required for a lot of robotic manipulation tasks. However, during manipulation, robots are expected to interact with unknown workpieces so that building predictive models which can…

Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of…

Non-adversarial robustness, also known as natural robustness, is a property of deep learning models that enables them to maintain performance even when faced with distribution shifts caused by natural variations in data. However, achieving…

Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of…

Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. There is an emerging literature on tackling this problem by…

Scene transfer for vision-based mobile robotics applications is a highly relevant and challenging problem. The utility of a robot greatly depends on its ability to perform a task in the real world, outside of a well-controlled lab…

We give a method for proactively identifying small, plausible shifts in distribution which lead to large differences in model performance. These shifts are defined via parametric changes in the causal mechanisms of observed variables, where…

Over the past decades, researchers and ML practitioners have come up with better and better ways to build, understand and improve the quality of ML models, but mostly under the key assumption that the training data is distributed…

Designing learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance. We present a general approach to this problem focusing on unsupervised…