English
Related papers

Related papers: Take Goodhart Seriously: Principled Limit on Gener…

200 papers

This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock…

General Finance · Quantitative Finance 2026-05-07 Sean Cao , Wei Jiang , Hui Xu

We study the generalization error of stochastic learning algorithms from an information-theoretic perspective, with a particular emphasis on deriving sharper bounds for differentially private algorithms. It is well known that the…

Information Theory · Computer Science 2026-04-20 Yanxiao Liu , Chun Hei Michael Shiu , Lele Wang , Deniz Gündüz

The inner alignment problem, which asserts whether an arbitrary artificial intelligence (AI) model satisfices a non-trivial alignment function of its outputs given its inputs, is undecidable. This is rigorously proved by Rice's theorem,…

Agile estimation techniques, particularly T-shirt sizing, are widely used in software development for their simplicity and utility in scoping work. However, when we apply these methods to artificial intelligence initiatives -- especially…

Software Engineering · Computer Science 2026-02-23 Raja Soundaramourty , Ozkan Kilic , Ramu Chenchaiah

Calibration of option pricing models is routinely repeated as markets evolve, yet modern systems lack an operator for removing data from a calibrated model without full retraining. When quotes become stale, corrupted, or subject to deletion…

Mathematical Finance · Quantitative Finance 2025-11-20 Ahmet Umur Özsoy

The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim at defending attacks constrained within low magnitude Lp norm bounds,…

Machine Learning · Computer Science 2022-10-19 Sravanti Addepalli , Samyak Jain , Gaurang Sriramanan , R. Venkatesh Babu

Most systems and learning algorithms optimize average performance or average loss -- one reason being computational complexity. However, many objectives of practical interest are more complex than simply average loss. This arises, for…

Machine Learning · Computer Science 2018-06-05 Daniel Alabi , Nicole Immorlica , Adam Tauman Kalai

General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…

Computation and Language · Computer Science 2026-05-19 Han Bao , Yue Huang , Xiaoda Wang , Zheyuan Zhang , Yujun Zhou , Carl Yang , Xiangliang Zhang , Yanfang Ye

Inverse optimization (IO) aims to determine optimization model parameters from observed decisions. However, IO is not part of a data scientist's toolkit in practice, especially as many general-purpose machine learning packages are widely…

Optimization and Control · Mathematics 2021-02-23 Elaheh H. Iraj , Daria Terekhov

Recent work have demonstrated that robustness (to "corruption") can be at odds with generalization. Adversarial training, for instance, aims to reduce the problematic susceptibility of modern neural networks to small data perturbations.…

Machine Learning · Statistics 2023-05-19 Amine Bennouna , Ryan Lucas , Bart Van Parys

We prove that Riemannian contraction in a supervised learning setting implies generalization. Specifically, we show that if an optimizer is contracting in some Riemannian metric with rate $\lambda > 0$, it is uniformly algorithmically…

Machine Learning · Computer Science 2022-01-27 Leo Kozachkov , Patrick M. Wensing , Jean-Jacques Slotine

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the…

Machine Learning · Statistics 2025-10-08 Eric Aubinais , Elisabeth Gassiat , Pablo Piantanida

In this paper we consider the following question: can we optimize objective functions from the training data we use to learn them? We formalize this question through a novel framework we call optimization from samples (OPS). In OPS, we are…

Data Structures and Algorithms · Computer Science 2016-11-17 Eric Balkanski , Aviad Rubinstein , Yaron Singer

Machine learning algorithms are now frequently used in sensitive contexts that substantially affect the course of human lives, such as credit lending or criminal justice. This is driven by the idea that `objective' machines base their…

Machine Learning · Computer Science 2019-01-17 Songül Tolan

Despite the widespread use of machine learning algorithms to solve problems of technological, economic, and social relevance, provable guarantees on the performance of these data-driven algorithms are critically lacking, especially when the…

Machine Learning · Computer Science 2019-03-18 Abed AlRahman Al Makdah , Vaibhav Katewa , Fabio Pasqualetti

Oversight and control, which we collectively call supervision, are often discussed as ways to ensure that AI systems are accountable, reliable, and able to fulfill governance and management requirements. However, the requirements for "human…

Artificial Intelligence · Computer Science 2025-11-04 David Manheim , Aidan Homewood

State-of-the-art machine learning algorithms demonstrate close to absolute performance in selected challenges. We provide arguments that the reason can be in low variability of the samples and high effectiveness in learning typical…

Computer Vision and Pattern Recognition · Computer Science 2018-07-25 Egor Illarionov , Roman Khudorozhkov

The definition and implementation of fairness in automated decisions has been extensively studied by the research community. Yet, there hides fallacious reasoning, misleading assertions, and questionable practices at the foundations of the…

Computers and Society · Computer Science 2023-06-05 Robert Lee Poe , Soumia Zohra El Mestari

Recently, there has been an increasing interest in the application of multiobjective optimization (MOO) in machine learning (ML). This interest is driven by the numerous real-life situations where multiple objectives must be optimized…

Machine Learning · Computer Science 2025-04-30 Junaid Akhter , Paul David Fährmann , Konstantin Sonntag , Sebastian Peitz , Daniel Schwietert

Many algorithms have been recently proposed for causal machine learning. Yet, there is little to no theory on their quality, especially considering finite samples. In this work, we propose a theory based on generalization bounds that…

Machine Learning · Statistics 2024-05-16 Daniel Csillag , Claudio José Struchiner , Guilherme Tegoni Goedert
‹ Prev 1 8 9 10 Next ›