arXiv subjects

Rūta Binkytė

Publications and source records attributed to Rūta Binkytė.

4 recordsLinked to original sources

arXiv2026

Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best

AI agents sometimes act aligned when they infer they are being tested, and differently when not. We argue this is not an anomaly but what current training regimes are structured to select for. Reinforcement-learning-based alignment folds norms and task pursuit into one policy: the system learns its norms from scored behavior, and scoring flattens them. Do not do X is learned as doing X costs something if noticed. On every datum training can produce, a policy that complies only when it might be observed is indistinguishable from one that complies always. The experiment that would tell them apart - scoring unobserved behavior - is a contradiction in terms. Conditional compliance is thus the most that behavioral training can be known to deliver. Agency sharpens the problem: agents operate mostly where no one is watching, and can act on whether they are watched. An iterated pipeline that trains against detected failures selects for passing detection, not for complying. This account unifies alignment faking, sandbagging, and evaluation-aware scheming. And it reorients the remedy: not deeper internalization but architecture, making violations unavailable rather than unchosen.

cs.AI↗

arXiv2024

Causal Discovery Under Local Privacy

Differential privacy is a widely adopted framework designed to safeguard the sensitive information of data providers within a data set. It is based on the application of controlled noise at the interface between the server that stores and processes the data, and the data consumers. Local differential privacy is a variant that allows data providers to apply the privatization mechanism themselves on their data individually. Therefore it provides protection also in contexts in which the server, or even the data collector, cannot be trusted. The introduction of noise, however, inevitably affects the utility of the data, particularly by distorting the correlations between individual data components. This distortion can prove detrimental to tasks such as causal discovery. In this paper, we consider various well-known locally differentially private mechanisms and compare the trade-off between the privacy they provide, and the accuracy of the causal structure produced by algorithms for causal learning when applied to data obfuscated by these mechanisms. Our analysis yields valuable insights for selecting appropriate local differentially private protocols for causal discovery tasks. We foresee that our findings will aid researchers and practitioners in conducting locally private causal discovery.

cs.CR↗

arXiv2023

Dissecting Causal Biases

Accurately measuring discrimination in machine learning-based automated decision systems is required to address the vital issue of fairness between subpopulations and/or individuals. Any bias in measuring discrimination can lead to either amplification or underestimation of the true value of discrimination. This paper focuses on a class of bias originating in the way training data is generated and/or collected. We call such class causal biases and use tools from the field of causality to formally define and analyze such biases. Four sources of bias are considered, namely, confounding, selection, measurement, and interaction. The main contribution of this paper is to provide, for each source of bias, a closed-form expression in terms of the model parameters. This makes it possible to analyze the behavior of each source of bias, in particular, in which cases they are absent and in which other cases they are maximized. We hope that the provided characterizations help the community better understand the sources of bias in machine learning applications.

cs.LG↗

arXiv2023

Shedding light on underrepresentation and Sampling Bias in machine learning

Accurately measuring discrimination is crucial to faithfully assessing fairness of trained machine learning (ML) models. Any bias in measuring discrimination leads to either amplification or underestimation of the existing disparity. Several sources of bias exist and it is assumed that bias resulting from machine learning is born equally by different groups (e.g. females vs males, whites vs blacks, etc.). If, however, bias is born differently by different groups, it may exacerbate discrimination against specific sub-populations. Sampling bias, is inconsistently used in the literature to describe bias due to the sampling procedure. In this paper, we attempt to disambiguate this term by introducing clearly defined variants of sampling bias, namely, sample size bias (SSB) and underrepresentation bias (URB). We show also how discrimination can be decomposed into variance, bias, and noise. Finally, we challenge the commonly accepted mitigation approach that discrimination can be addressed by collecting more samples of the underrepresented group.

cs.LG↗