Alex Ororbia

Hong Yang, Devroop Kar, Qi Yu et al.

Why do state-of-the-art OOD detection methods exhibit catastrophic failure when models are trained on single-domain datasets? We provide the first theoretical explanation for this phenomenon through the lens of information theory. We prove that supervised learning on single-domain data inevitably produces domain feature collapse -- representations where I(x_d; z) = 0, meaning domain-specific information is completely discarded. This is a fundamental consequence of information bottleneck optimization: models trained on single domains (e.g., medical images) learn to rely solely on class-specific features while discarding domain features, leading to catastrophic failure when detecting out-of-domain samples (e.g., achieving only 53% FPR@95 on MNIST). We extend our analysis using Fano's inequality to quantify partial collapse in practical scenarios. To validate our theory, we introduce Domain Bench, a benchmark of single-domain datasets, and demonstrate that preserving I(x_d; z) > 0 through domain filtering (using pretrained representations) resolves the failure mode. While domain filtering itself is conceptually straightforward, its effectiveness provides strong empirical evidence for our information-theoretic framework. Our work explains a puzzling empirical phenomenon, reveals fundamental limitations of supervised learning in narrow domains, and has broader implications for transfer learning and when to fine-tune versus freeze pretrained models.

Rodney A Sanchez, Ferat Sahin, Alex Ororbia et al.

Advancements in reinforcement learning have produced a variety of complex and useful intrinsic driving forces; crucially, these drivers operate under a direct conditioning paradigm. This form of conditioning limits our agents' capacity by restricting how they learn from the environment as well as from others. Off-policy or learn-by-example methods can learn from demonstrators' representations, but they require access to the demonstrating agent's policies or their reward functions. Our work overcomes this direct sampling limitation by introducing vicarious conditioning as an intrinsic reward mechanism. We draw from psychological and biological literature to provide a foundation for vicarious conditioning and use memory-based methods to implement its four steps: attention, retention, reproduction, and reinforcement. Crucially, our vicarious conditioning paradigms support low-shot learning and do not require the demonstrator agent's policy nor its reward functions. We evaluate our approach in the MiniWorld Sidewalk environment, one of the few public environments that features a non-descriptive terminal condition (no reward provided upon agent death), and extend it to Box2D's CarRacing environment. Our results across both environments demonstrate that vicarious conditioning enables longer episode lengths by discouraging the agent from non-descriptive terminal conditions and guiding the agent toward desirable states. Overall, this work emulates a cognitively-plausible learning paradigm better suited to problems such as single-life learning or continual learning.

Devroop Kar, Zimeng Lyu, Sheeraja Rajakrishnan et al.

Stock trading has always been a challenging task due to the highly volatile nature of the stock market. Making sound trading decisions to generate profit is particularly difficult under such conditions. To address this, we propose four novel loss functions to drive decision-making for a portfolio of stocks. These functions account for the potential profits or losses based with respect to buying or shorting respective stocks, enabling potentially any artificial neural network to directly learn an effective trading strategy. Despite the high volatility in stock market fluctuations over time, training time-series models such as transformers on these loss functions resulted in trading strategies that generated significant profits on a portfolio of 50 different S&P 500 company stocks as compared to a benchmark reinforcment learning techniques and a baseline buy and hold method. As an example, using 2021, 2022 and 2023 as three test periods, the Crossformer model adapted with our best loss function was most consistent, resulting in returns of 51.42%, 51.04% and 48.62% respectively. In comparison, the best performing state-of-the-art reinforcement learning methods, PPO and DDPG, only delivered maximum profits of around 41%, 2.81% and 41.58% for the same periods. The code is available at https://anonymous.4open.science/r/bandit-stock-trading-58C8/README.md.

Hong Yang, Devroop Kar, Qi Yu et al.

Out-of-distribution (OOD) detection methods perform well on multi-domain benchmarks, yet many practical systems are trained on single-domain data. We show that this regime induces a geometric failure mode, Domain-Sensitivity Collapse (DSC): supervised training compresses features into a low-rank class subspace and suppresses directions that carry domain-shift signal. We provide theory showing that, under DSC, distance- and logit-based OOD scores lose sensitivity to domain shift. We then introduce Teacher-Guided Training (TGT), which distills class-suppressed residual structure from a frozen multi-domain teacher (DINOv2) into the student during training. The teacher and auxiliary head are discarded after training, adding no inference overhead. Across eight single-domain benchmarks, TGT yields large far-OOD FPR@95 reductions for distance-based scorers: MDS improves by 11.61 pp, ViM by 10.78 pp, and kNN by 12.87 pp (ResNet-50 average), while maintaining or slightly improving in-domain OOD and classification accuracy.

Xiao Yang, Dafang He, Wenyi Huang et al.

Physical library collections are valuable and long standing resources for knowledge and learning. However, managing books in a large bookshelf and finding books on it often leads to tedious manual work, especially for large book collections where books might be missing or misplaced. Recently, deep neural models, such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) have achieved great success for scene text detection and recognition. Motivated by these recent successes, we aim to investigate their viability in facilitating book management, a task that introduces further challenges including large amounts of cluttered scene text, distortion, and varied lighting conditions. In this paper, we present a library inventory building and retrieval system based on scene text reading methods. We specifically design our scene text recognition model using rich supervision to accelerate training and achieve state-of-the-art performance on several benchmark datasets. Our proposed system has the potential to greatly reduce the amount of human labor required in managing book inventories as well as the space needed to store book information.