相关论文: Learning When to Trust in Contextual Bandits

Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning trace might fail remains difficult. Confidence estimation…

In the classical contextual bandits problem, in each round $t$, a learner observes some context $c$, chooses some action $i$ to perform, and receives some reward $r_{i,t}(c)$. We consider the variant of this problem where in addition to…

Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness into an opportunity: one can take advantage of distribution…

We consider an online learning problem with one-sided feedback, in which the learner is able to observe the true label only for positively predicted instances. On each round, $k$ instances arrive and receive classification outcomes…

Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ only by some regularizers either at inner maximization or outer minimization steps. Being repetitive in nature during the inner maximization…

The contextual bandit problem, where agents arrive sequentially with personal contexts and the system adapts its arm allocation decisions accordingly, has recently garnered increasing attention for enabling more personalized outcomes.…

In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to…

As the era of autonomous agents making decisions on behalf of users unfolds, ensuring contextual integrity (CI) -- what is the appropriate information to share while carrying out a certain task -- becomes a central question to the field. We…

This paper studies bandit problems where an agent has access to offline data that might be utilized to potentially improve the estimation of each arm's reward distribution. A major obstacle in this setting is the existence of compound…

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…

Institutions with limited data and computing resources often outsource model training to third-party providers in a semi-honest setting, assuming adherence to prescribed training protocols with pre-defined learning paradigm (e.g.,…

We study the problem of learning robust classifiers where the classifier will receive a perturbed input. Unlike robust PAC learning studied in prior work, here the clean data and its label are also adversarially chosen. We formulate this…

We consider the contextual bandit problem where at each time, the agent only has access to a noisy version of the context and the error variance (or an estimator of this variance). This setting is motivated by a wide range of applications…

In many fields such as digital marketing, healthcare, finance, and robotics, it is common to have a well-tested and reliable baseline policy running in production (e.g., a recommender system). Nonetheless, the baseline policy is often…

In contextual linear bandits, the reward function is assumed to be a linear combination of an unknown reward vector and a given embedding of context-arm pairs. In practice, the embedding is often learned at the same time as the reward…

We study linear contextual bandits with access to a large, confounded, offline dataset that was sampled from some fixed policy. We show that this problem is closely related to a variant of the bandit problem with side information. We…

This paper investigates the challenges of optimal online policy learning under missing data. State-of-the-art algorithms implicitly assume that rewards are always observable. I show that when rewards are missing at random, the Upper…

Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search. Generalized linear models (logistical regression in particular) have demonstrated stronger performance than linear models in…

Many continuous-control problems ship with a competent but suboptimal controller (a tuned PID, a hand-designed gait). A growing family of methods uses such controllers as queryable experts during RL, but each method has been proposed in…

Metamorphic Testing is a software testing paradigm which aims at using necessary properties of a system-under-test, called metamorphic relations, to either check its expected outputs, or to generate new test cases. Metamorphic Testing has…