Related papers: Adversarial Stress Tests for Quantum Certification
Digital signatures play an important role in software distribution, modern communication and financial transactions, where it is important to detect forgery and tampering. Signatures are a cryptographic technique for validating the…
We present an accreditation protocol for the outputs of noisy intermediate-scale quantum devices. By testing entire circuits rather than individual gates, our accreditation protocol can provide an upper-bound on the variation distance…
Certification of quantum devices received from unknown providers is a primary requirement before utilizing the devices for any information processing task. Here, we establish a protocol for certification of a particular set of $d$-outcome…
Semi-supervised domain adaptation (SSDA) has been widely studied due to its ability to utilize a few labeled target data to improve the generalization ability of the model. However, existing methods only consider designing certain…
The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled…
Although an ever-growing number of applications employ deep learning based systems for prediction, decision-making, or state estimation, almost no certification processes have been established that would allow such systems to be deployed in…
We propose a new conditional dependence measure and a statistical test for conditional independence. The measure is based on the difference between analytic kernel embeddings of two well-suited distributions evaluated at a finite set of…
Amortized Bayesian inference (ABI) with neural networks can solve probabilistic inverse problems orders of magnitude faster than classical methods. However, ABI is not yet sufficiently robust for widespread and safe application. When…
The expansion of machine learning into dynamic environments presents challenges in handling open-world problems where label shift, covariate shift, and unknown classes emerge. Post-training methods have been explored to address these…
Pre-trained models excel on NLI benchmarks like SNLI and MultiNLI, but their true language understanding remains uncertain. Models trained only on hypotheses and labels achieve high accuracy, indicating reliance on dataset biases and…
In the Quantum Supremacy regime, quantum computers may overcome classical machines on several tasks if we can estimate, mitigate, or correct unavoidable hardware noise. Estimating the error requires classical simulations, which become…
We propose a semi-supervised text classifier based on self-training using one positive and one negative property of neural networks. One of the weaknesses of self-training is the semantic drift problem, where noisy pseudo-labels accumulate…
In this paper, we focus on the challenge of individual variability in affective brain-computer interfaces (aBCI), which employs electroencephalogram (EEG) signals to monitor and recognize human emotional states, thereby facilitating the…
We propose a non-convex training objective for robust binary classification of data sets in which label noise is present. The design is guided by the intention of solving the resulting problem by adiabatic quantum optimization. Two…
We address the computational and theoretical limitations of current distributional alignment methods for source-free unsupervised domain adaptation (SFUDA) using source class-mean features. In particular, we focus on estimating…
Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.…
In semi-supervised learning, the paradigm of self-training refers to the idea of learning from pseudo-labels suggested by the learner itself. Across various domains, corresponding methods have proven effective and achieve state-of-the-art…
In learning with noisy labels, for every instance, its label can randomly walk to other classes following a transition distribution which is named a noise model. Well-studied noise models are all instance-independent, namely, the transition…
Nowadays, pretrained models are increasingly used as general-purpose backbones and adapted at test-time to downstream environments where target data are scarce and unlabeled. While this paradigm has proven effective for improving clean…
We study a protocol-level test for weak-label benchmarks: whether benchmark outputs change when the provided evidence is intervened on. Metadata-only shortcut checks answer a different question, namely whether outputs are predictable from…