Related papers: Improved Robust Algorithms for Learning with Discr…
Label noise will degenerate the performance of deep learning algorithms because deep neural networks easily overfit label errors. Let X and Y denote the instance and clean label, respectively. When Y is a cause of X, according to which many…
We introduce \textit{Feedback Descent}, a framework that optimizes text artifacts -- prompts, code, and molecules -- through structured textual feedback, rather than relying solely on scalar rewards. By preserving detailed critiques instead…
Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…
The needs for precisely estimating a student's academic performance have been emphasized with an increasing amount of attention paid to Intelligent Tutoring System (ITS). However, since labels for academic performance, such as test scores,…
Features in product lines and highly configurable systems can interact in ways that are contrary to developers' intent. Current methods to identify such unanticipated feature interactions are costly and inadequate. To address this problem…
Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing…
Conformal prediction has emerged as an effective strategy for uncertainty quantification by modifying a model to output sets of labels instead of a single label. These prediction sets come with the guarantee that they contain the true label…
Particle dynamics and multi-agent systems provide accurate dynamical models for studying and forecasting the behavior of complex interacting systems. They often take the form of a high-dimensional system of differential equations…
Humans often juggle multiple, sometimes conflicting objectives and shift their priorities as circumstances change, rather than following a fixed objective function. In contrast, most computational decision-making and multi-objective RL…
After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking.…
Learning recommender systems with multi-class optimization objective is a prevalent setting in recommendation. However, as observed user feedback often accounts for a tiny fraction of the entire item pool, the standard Softmax loss tends to…
Machine learning has achieved remarkable success across a wide range of applications, yet many of its most effective methods rely on access to large amounts of labeled data or extensive online interaction. In practice, acquiring…
Contrastive learning has proven instrumental in learning unbiased representations of data, especially in complex environments characterized by high-cardinality and high-dimensional sensitive information. However, existing approaches within…
Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded…
Federated learning is proposed as a machine learning setting to enable distributed edge devices, such as mobile phones, to collaboratively learn a shared prediction model while keeping all the training data on device, which can not only…
Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models (LLMs) with human preferences. To learn the reward function, most existing RLHF algorithms use the…
When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we…
Distributionally robust policy learning aims to find a policy that performs well under the worst-case distributional shift, and yet most existing methods for robust policy learning consider the worst-case joint distribution of the covariate…
Dynamic feature selection, where we sequentially query features to make accurate predictions with a minimal budget, is a promising paradigm to reduce feature acquisition costs and provide transparency into a model's predictions. The problem…
We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…