The curse of dimensionality presents a pervasive challenge in optimization problems, with exponential expansion of the search space rapidly causing traditional algorithms to become inefficient or infeasible. An adaptive sampling strategy is presented to accelerate optimization in this domain as an alternative to uniform quasi-Monte Carlo (QMC) methods. This method, referred to as Hyperellipsoid Density Sampling (HDS), generates its sequences by defining multiple hyperellipsoids throughout the search space. HDS uses three types of unsupervised learning algorithms to circumvent high-dimensional geometric calculations, producing an intelligent, non-uniform sample sequence that exploits statistically promising regions of the parameter space and improves final solution quality in high-dimensional optimization problems. A key feature of the method is optional Gaussian weights, which may be provided to influence the sample distribution towards known locations of interest. This capability makes HDS versatile for applications beyond optimization, providing a focused, denser sample distribution where models need to concentrate their efforts on specific, non-uniform regions of the parameter space. The method was evaluated against Sobol, a standard QMC method, using differential evolution (DE) on the 29 CEC2017 benchmark test functions. The results show statistically significant improvements in solution geometric mean error (p < 0.05), with average performance gains ranging from 3% in 30D to 37% in 10D. This paper demonstrates the efficacy of HDS as a robust alternative to QMC sampling for high-dimensional optimization.

Reliable data is a cornerstone of modern organizational systems. A notable data integrity challenge stems from label bias, which refers to systematic errors in a label, a covariate that is central to a quantitative analysis, such that its quality differs across social groups. This type of bias has been conceptually and empirically explored and is widely recognized as a pressing issue across critical domains. However, effective methodologies for addressing it remain scarce. In this work, we propose Decoupled Confident Learning (DeCoLe), a principled machine learning based framework specifically designed to detect mislabeled instances in datasets affected by label bias, enabling bias aware mislabelling detection and facilitating data quality improvement. We theoretically justify the effectiveness of DeCoLe and evaluate its performance in the impactful context of hate speech detection, a domain where label bias is a well documented challenge. Empirical results demonstrate that DeCoLe excels at bias aware mislabeling detection, consistently outperforming alternative approaches for label error detection. Our work identifies and addresses the challenge of bias aware mislabeling detection and offers guidance on how DeCoLe can be integrated into organizational data management practices as a powerful tool to enhance data reliability.

Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora. These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions. In this paper, we compare ten public "medical" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting and supervised fine-tuning regimes for medical question-answering (QA). For instance, across all tasks and model pairs we consider in the 3-shot setting, medical LLMs only outperform their base models in 22.7% of cases, reach a (statistical) tie in 36.8% of cases, and are significantly worse than their base models in the remaining 40.5% of cases. Our conclusions are based on (i) comparing each medical model head-to-head, directly against the corresponding base model; (ii) optimizing the prompts for each model separately in zero-/few-shot prompting; and (iii) accounting for statistical uncertainty in comparisons. While these basic practices are not consistently adopted in the literature, our ablations show that they substantially impact conclusions. Meanwhile, we find that after fine-tuning on specific QA tasks, medical LLMs can show performance improvements, but the benefits do not carry over to tasks based on clinical notes. Our findings suggest that state-of-the-art general-domain models may already exhibit strong medical knowledge and reasoning capabilities, and offer recommendations to strengthen the conclusions of future studies.

Deep reinforcement learning (RL) provides powerful methods for training optimal sequential decision-making agents. As collecting real-world interactions can entail additional costs and safety risks, the common paradigm of sim2real conducts training in a simulator, followed by real-world deployment. Unfortunately, RL agents easily overfit to the choice of simulated training environments, and worse still, learning ends when the agent masters the specific set of simulated environments. In contrast, the real world is highly open-ended, featuring endlessly evolving environments and challenges, making such RL approaches unsuitable. Simply randomizing over simulated environments is insufficient, as it requires making arbitrary distributional assumptions and can be combinatorially less likely to sample specific environment instances that are useful for learning. An ideal learning process should automatically adapt the training environment to maximize the learning potential of the agent over an open-ended task space that matches or surpasses the complexity of the real world. This thesis develops a class of methods called Unsupervised Environment Design (UED), which aim to produce such open-ended processes. Given an environment design space, UED automatically generates an infinite sequence or curriculum of training environments at the frontier of the learning agent's capabilities. Through extensive empirical studies and theoretical arguments founded on minimax-regret decision theory and game theory, the findings in this thesis show that UED autocurricula can produce RL agents exhibiting significantly improved robustness and generalization to previously unseen environment instances. Such autocurricula are promising paths toward open-ended learning systems that achieve more general intelligence by continually generating and mastering additional challenges of their own design.

This is the first in a series of posts that illustrate what our data team is up to, experimenting with, and building'under the hood' at CitizenNet. He has been involved in web-scale machine learning and information retrieval for over 10 years. One of the first posts we published spoke at a high level of the technical problem CitizenNet is trying to solve. In essence, we are trying to predict what combinations of demographic and interest targets will be interested in some piece of content. On the CitizenNet platform, a user would create a project that would define (broadly) the target audience, the pieces of Facebook content they are looking to promote, and other campaign and financial information. Behind the scenes, a robust prediction system builds the targets for the project.

Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code. A particularly exciting aspect of LLMs is their knack for few-shot and zero-shot learning: they can learn to perform a task with very few examples. Few-shotting has particular synergies in software engineering, where there are a lot of phenomena (identifier names, APIs, terminology, coding patterns) that are known to be highly project-specific. However, project-specific data can be quite limited, especially early in the history of a project; thus the few-shot learning capacity of LLMs might be very relevant. In this paper, we investigate the use few-shot training with the very large GPT (Generative Pre-trained Transformer) Codex model, and find evidence suggesting that one can significantly surpass state-of-the-art models for code-summarization, leveraging project-specific training.

How data is represented and operationalized is critical for building computational solutions that are both effective and efficient. A common approach is to represent data objects as binary vectors, denoted \textit{hash codes}, which require little storage and enable efficient similarity search through direct indexing into a hash table or through similarity computations in an appropriate space. Due to the limited expressibility of hash codes, compared to real-valued representations, a core open challenge is how to generate hash codes that well capture semantic content or latent properties using a small number of bits, while ensuring that the hash codes are distributed in a way that does not reduce their search efficiency. State of the art methods use representation learning for generating such hash codes, focusing on neural autoencoder architectures where semantics are encoded into the hash codes by learning to reconstruct the original inputs of the hash codes. This thesis addresses the above challenge and makes a number of contributions to representation learning that (i) improve effectiveness of hash codes through more expressive representations and a more effective similarity measure than the current state of the art, namely the Hamming distance, and (ii) improve efficiency of hash codes by learning representations that are especially suited to the choice of search method. The contributions are empirically validated on several tasks related to similarity search and recommendation.

The construction of efficient and effective decision trees remains a key topic in machine learning because of their simplicity and flexibility. A lot of heuristic algorithms have been proposed to construct near-optimal decision trees. ID3, C4.5 and CART are classical decision tree algorithms and the split criteria they used are Shannon entropy, Gain Ratio and Gini index respectively. All the split criteria seem to be independent, actually, they can be unified in a Tsallis entropy framework. Tsallis entropy is a generalization of Shannon entropy and provides a new approach to enhance decision trees' performance with an adjustable parameter $q$. In this paper, a Tsallis Entropy Criterion (TEC) algorithm is proposed to unify Shannon entropy, Gain Ratio and Gini index, which generalizes the split criteria of decision trees. More importantly, we reveal the relations between Tsallis entropy with different $q$ and other split criteria. Experimental results on UCI data sets indicate that the TEC algorithm achieves statistically significant improvement over the classical algorithms.