Related papers: Safety Synthesis Sans Specification
This thesis presents a computational theory of unsupervised language acquisition, precisely defining procedures for learning language from ordinary spoken or written utterances, with no explicit help from a teacher. The theory is based…
Self-supervised learning (SSL) has grown in interest within the speech processing community, since it produces representations that are useful for many downstream tasks. SSL uses global and contextual methods to produce robust…
Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings…
State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific…
This paper formalizes a latent variable inference problem we call {\em supervised pattern discovery}, the goal of which is to find sets of observations that belong to a single ``pattern.'' We discuss two versions of the problem and prove…
We study bounded deviation of non-deterministic finite transducers under the Hamming distance: the bounded comparison problem asks, given two transducers and $k \in \mathbb{N}$, whether for every input the two transducers produce words at…
Speech language models (SLMs) are systems of systems: independent components that unite to achieve a common goal. Despite their heterogeneous nature, SLMs are often studied end-to-end; how information flows through the pipeline remains…
We introduce a notion of distance between supervised learning problems, which we call the Risk distance. This distance, inspired by optimal transport, facilitates stability results; one can quantify how seriously issues like sampling bias,…
While safe reinforcement learning (RL) holds great promise for many practical applications like robotics or autonomous cars, current approaches require specifying constraints in mathematical form. Such specifications demand domain…
Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and…
Artificial intelligence (AI) has been advancing at a fast pace and it is now poised for deployment in a wide range of applications, such as autonomous systems, medical diagnosis and natural language processing. Early adoption of AI…
Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance. However, the process of collecting and labeling such data can be expensive and time-consuming. Self-supervised…
With the increasing prevalence of complex vision-based sensing methods for use in obstacle identification and state estimation, characterizing environment-dependent measurement errors has become a difficult and essential part of modern…
This paper addresses source tracing in synthetic speech-identifying generative systems behind manipulated audio via speaker recognition-inspired pipelines. While prior work focuses on spoofing detection, source tracing lacks robust…
In this paper, we study the technical problem of developing conversational agents that can quickly adapt to unseen tasks, learn task-specific communication tactics, and help listeners finish complex, temporally extended tasks. We find that…
Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-training uses different objectives to shape different behaviors, we argue that unlearning…
Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…
Confident prediction is highly relevant in machine learning; for example, in applications such as medical diagnoses, wrong prediction can be fatal. For classification, there already exist procedures that allow to not classify data when the…
Recent rapid developments in reinforcement learning algorithms have been giving us novel possibilities in many fields. However, due to their exploring property, we have to take the risk into consideration when we apply those algorithms to…
Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…