Zachary Izzo is a Researcher in the Machine Learning Department at NEC Laboratories America in Princeton, NJ. He received his PhD in Mathematics from Stanford University and his BS in Mathematics from the Massachusetts Institute of Technology. His research develops mathematically rigorous methods to understand when and why machine learning models work, with a recent focus on the foundations and interpretability of large language models.
Recent work includes a provably convergent algorithm for identifying patient subgroups with differential treatment response, and theoretical results on length generalization in transformers. By advancing methods that enhance interpretability and adaptability, his research directly contributes to NEC’s mission to build intelligent, resilient AI technologies that can operate in complex, data-rich real-world settings. His contributions help extend the frontier of AI toward systems that are not only accurate but also dependable and actionable in practice.
NEC Labs America is proud to attend NeurIPS 2024 in Vancouver, Canada from December 10-15. Zachary Izzo will present Subgroup Discovery with the Cox Model, Shaobo Han will present VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks and Jonathan Warrell will present Discrete-Continuous Variational Optimization with Local Gradients.
The problem of calibrating deep neural networks (DNNs) is gaining attention, as these networks are becoming central to many real-world applications. Different attempts have been made to counter the poor calibration of DNNs. Amongst others, train-time calibration methods have unfolded as an effective class for improving model calibration. Motivated by this, we propose a novel train-time calibration method that is built on a new auxiliary loss formulation, namely multiclass alignment of confidences with the gradually softened ground truth occurrences (MACSO). It is developed on the intuition that, for a class, the gradually softened ground truth occurrences distribution is a suitable non-zero entropy signal whose better alignment withthe predicted confidences distribution is positively correlated with reducing the model calibration error. In our train-time approach, besides simply aligning the two distributions, e.g., via their means or KL divergence, we propose to quantify the linear correlation between the two distributions, which preserves the relations among them, thereby further improving the calibration performance. Finally, we also reveal that MACSO posses desirable theoretical properties. Extensive results on several challenging datasets, featuring in and out-of-domain scenarios, class imbalanced problem, and a medical image classification task, validate the efficacy of our method against state-of-the-art train-time calibration methods.
We are thrilled to announce the launch of our latest research initiative, the Trustworthy Generative AI Project. This ambitious project is set to revolutionize how we interact with multimodal content by developing cutting-edge generative models capable of compositional generation and reasoning across text, images, reports, and even 3D videos.
We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. We apply this approach to a case study of scientific peer review in AI conferences that took place after the release of ChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggest that between 6.5% and 16.9% of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i.e. beyond spell-checking or minor writing updates. The circumstances in which generated text occurs offer insight into user behavior: the estimated fraction of LLM-generated text is higher in reviews which report lower confidence, were submitted close to the deadline, and from reviewers who are less likely to respond to author rebuttals. We also observe corpus-level trends in generated text which may be too subtle to detect at the individual level, and discuss the implications of such trends on peer review. We call for future interdisciplinary work to examine how LLM use is changing our information and knowledge practices.
In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model development.Differential privacy (DP) has emerged as one canonical standard for provable privacy. However, DPs strong theoretical guarantees often come at the cost of a large drop in its utility for machine learning; and DP guarantees themselves are difficult to interpret. In this work, we propose a novel privacy notion, membership inference privacy (MIP), as a steptowards addressing these challenges. We give a precise characterization of the relationship between MIP and DP, and show that in some cases, MIP can be achieved using less amountof randomness compared to the amount required for guaranteeing DP, leading to smaller drop in utility. MIP guarantees are also easily interpretable in terms of the success rate of membership inference attacks in a simple random subsampling setting. As a proof of concept, we also provide a simple algorithm for guaranteeing MIP without needing to guarantee DP.
NEC Labs America is proud to be a Silver Sponsor for NeurIPS 2023 in New Orleans from December 10-16. Visit our booth to meet our team and learn about our intern opportunities in machine learning, data science, media analytics and integrated systems. Also, our Vijay Kumar.B.G, Samuel Schulter & Manmohan Chandraker, along with Zaid Khan, Northeastern University and Yun Fu, UC San Diego will present a paper, Exploring Question Decomposition for Zero-Shot VQA.
