Related papers: HERA-B Framework for Online Calibration and Alignm…
Scale-calibrated ranking systems are ubiquitous in real-world applications nowadays, which pursue accurate ranking quality and calibrated probabilistic predictions simultaneously. For instance, in the advertising ranking system, the…
Despite the importance of having a measure of confidence in recommendation results, it has been surprisingly overlooked in the literature compared to the accuracy of the recommendation. In this dissertation, I propose a model calibration…
Analyzing classification model performance is a crucial task for machine learning practitioners. While practitioners often use count-based metrics derived from confusion matrices, like accuracy, many applications, such as weather…
Conformal prediction is a framework for uncertainty quantification that constructs prediction sets for previously unseen data, guaranteeing coverage of the true label with a specified probability. However, the efficiency of these prediction…
The importance of Reinforcement Learning from Human Feedback (RLHF) in aligning large language models (LLMs) with human values cannot be overstated. RLHF is a three-stage process that includes supervised fine-tuning (SFT), reward learning,…
We present a customizable online optimization framework for real-time EV smart charging to be readily implemented at real large-scale charging facilities. Notably, due to real-world constraints, we designed our framework around 3 main…
Conformal prediction provides a principled framework for uncertainty quantification with finite-sample coverage guarantees. While recent work has extended conformal prediction to online and sequential settings, existing methods typically…
Post-training is the decisive step for converting a pretrained video generator into a production-oriented model that is instruction-following, controllable, and robust over long temporal horizons. This report presents a systematical…
Calibration of neural networks is a topical problem that is becoming more and more important as neural networks increasingly underpin real-world applications. The problem is especially noticeable when using modern neural networks, for which…
Learning the dynamics of robots from data can help achieve more accurate tracking controllers, or aid their navigation algorithms. However, when the actual dynamics of the robots change due to external conditions, on-line adaptation of…
Assessing uncertainty is an important step towards ensuring the safety and reliability of machine learning systems. Existing uncertainty estimation techniques may fail when their modeling assumptions are not met, e.g. when the data…
The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior. While the former need is…
The study of online decision-making problems that leverage contextual information has drawn notable attention due to their significant applications in fields ranging from healthcare to autonomous systems. In modern applications, contextual…
To solve multi-step manipulation tasks in the real world, an autonomous robot must take actions to observe its environment and react to unexpected observations. This may require opening a drawer to observe its contents or moving an object…
The LHCb experiment at CERN has undergone a comprehensive upgrade, including a complete re-design of the trigger system into a hybrid-architecture, software-only system that delivers ten times more interesting signals per unit time than its…
Reliable long-horizon value prediction is difficult in offline reinforcement learning because fitted value methods combine bootstrapping, function approximation, and distribution shift, while standard guarantees often require Bellman…
In this paper we propose a model-based approach to the design of online optimization algorithms, with the goal of improving the tracking of the solution trajectory (trajectories) w.r.t. state-of-the-art methods. We focus first on quadratic…
In a linear tomosynthesis scanner designed for imaging histologic samples of several centimeter size at 10 micrometer resolution, the mechanical instability of the scanning stage (+/-10 micrometers) exceeded the resolution of the image…
After a highly successful first data taking period at the LHC, the LHCb experiment developed a new trigger strategy with a real-time reconstruction, alignment and calibration for Run II. This strategy relies on offline-like track…
In this paper we propose a recursive online algorithm for estimating the parameters of a time-varying ARCH process. The estimation is done by updating the estimator at time point $t-1$ with observations about the time point $t$ to yield an…