Semi-supervised learning (SSL) often suffers under class imbalance, where pseudo-labeling amplifies majority bias and suppresses minority performance. We address this issue with a lightweight framework that, to our knowledge, is the first to introduce Proportion Loss from learning from label proportions (LLP) into SSL as a regularization term. Proportion Loss aligns model predictions with the global class distribution, mitigating bias across both majority and minority classes. To further stabilize training, we formulate a stochastic variant that accounts for […]

Ver mais

arXiv:2509.13130v3 Announce Type: replace-cross Abstract: Prediction sets offer a binary inclusion/exclusion for each element at the same fixed confidence level. We generalize to fuzzy prediction sets, which exclude elements at their own data-driven confidence level. Our key insight is that a fuzzy prediction set emph{is} an e-value, capturing precisely what e-values bring to predictive inference. Fuzzy prediction sets inherit the merging properties of their e-value, offer richer guarantees to decision-makers. We also show in what sense optimal e-values […]

Ver mais

arXiv:2405.01425v4 Announce Type: replace-cross Abstract: We present a new random walk for uniformly sampling high-dimensional convex bodies. It achieves state-of-the-art runtime complexity with stronger guarantees on the output than previously known, namely in R’enyi divergence (which implies TV, $mathcal{W}_2$, KL, $chi^2$). The proof departs from known approaches for polytime algorithms for the problem — we utilize a stochastic diffusion perspective to show contraction to the target distribution with the rate of convergence determined by functional isoperimetric constants of […]

Ver mais

arXiv:2601.15299v1 Announce Type: new Abstract: Topic modeling is a crucial technique for extracting latent themes from unstructured text data, particularly valuable in analyzing survey responses. However, traditional methods often only consider free-text responses and do not natively incorporate structured or categorical survey responses for topic modeling. And they produce abstract topics, requiring extensive human interpretation. To address these limitations, we propose the Multi-Agent LLM Topic Modeling Framework (MALTopic). This framework decomposes topic modeling into specialized tasks executed by […]

Ver mais

arXiv:2602.10212v1 Announce Type: new Abstract: Previous empirical studies have shown that LoRA achieves accuracy comparable to full-parameter methods on downstream fine-tuning tasks, even for rank-1 updates. By contrast, the theoretical underpinnings of the dependence of LoRA’s accuracy on update rank remain relatively unexplored. In this work, we compare the accuracy of rank-r LoRA updates against full-parameter updates for fine-tuning tasks from a dynamical systems perspective. We perform gradient flow analysis in both full-rank and low-rank regimes to establish […]

Ver mais

Recognizing the substantial computational cost of backpropagation (BP), non-BP methods have emerged as attractive alternatives for efficient learning on emerging neuromorphic systems. However, existing non-BP approaches still face critical challenges in efficiency and scalability. Inspired by neural representations and dynamic mechanisms in the brain, we propose a perturbation-based approach called LOw-rank Cluster Orthogonal (LOCO) weight modification. We find that low-rank is an inherent property of perturbation-based algorithms. Under this condition, the orthogonality constraint limits the variance of the […]

Ver mais

Active learning (AL) strategies aim to train high-performance models with minimal labeling efforts, only selecting the most informative instances for annotation. Current approaches to evaluating data informativeness predominantly focus on the data’s distribution or intrinsic information content and do not directly correlate with downstream task performance, such as mean average precision (mAP) in object detection. Thus, we propose Performance-guided (i.e. mAP-guided) Reinforced Active Learning for Object Detection (MGRAL), a novel approach that leverages the concept of expected model […]

Ver mais

arXiv:2510.13763v2 Announce Type: replace Abstract: Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging modern generative methods like diffusion models to map observed data to model parameters or future predictions. These approaches yield posterior or posterior-predictive samples for new datasets without requiring further simulator calls after training on simulated parameter-data pairs. However, their applicability is often limited by the prior distribution(s) used to generate model parameters […]

Ver mais