Search for: All records

Online reinforcement learning (RL) enhances policies through direct interactions with the environment, but faces challenges related to sample efficiency. In contrast, offline RL leverages extensive pre-collected data to learn policies, but often produces suboptimal results due to limited data coverage. Recent efforts integrate offline and online RL in order to harness the advantages of both approaches. However, effectively combining online and offline RL remains challenging due to issues that include catastrophic forgetting, lack of robustness to data quality and limited sample efficiency in data utilization. In an effort to address these challenges, we introduce A3RL, which incorporates a novel confidence aware Active Advantage Aligned (A3) sampling strategy that dynamically prioritizes data aligned with the policy's evolving needs from both online and offline sources, optimizing policy improvement. Moreover, we provide theoretical insights into the effectiveness of our active sampling strategy and conduct diverse empirical experiments and ablation studies, demonstrating that our method outperforms competing online RL techniques that leverage offline data. Our code will be publicly available at:this https URL. 

Students bring different levels of interest to learning experiences, which impacts how they engage with learning materials. This study aims to understand the relationship between student's interest levels and their scientific observation behaviors within a Minecraft-based learning system. Motivated by the growing interest in integrating human-AI collaboration within educational research, we combine the capabilities of Large Language Models (LLMs) with the expertise of human researchers to capture the emerging themes within students’ observations. Using epistemic network analysis, we then visualized and compared the observational patterns of students with high and low situational interest. Our findings indicate that students with higher situational interest tend to make observations across a broader range of topics, with a particular emphasis on scientific content. These results highlight the potential for developing timely interventions to support students with low situational interest. 

While training models and labeling data are resource-intensive, a wealth of pre-trained models and unlabeled data exists. To effectively utilize these resources, we present an approach to actively select pre-trained models while minimizing labeling costs. We frame this as an online contextual active model selection problem: At each round, the learner receives an unlabeled data point as a context. The objective is to adaptively select the best model to make a prediction while limiting label requests. To tackle this problem, we propose CAMS, a contextual active model selection algorithm that relies on two novel components: (1) a contextual model selection mechanism, which leverages context information to make informed decisions about which model is likely to perform best for a given context, and (2) an active query component, which strategically chooses when to request labels for data points, minimizing the overall labeling cost. We provide rigorous theoretical analysis for the regret and query complexity under both adversarial and stochastic settings. Furthermore, we demonstrate the effectiveness of our algorithm on a diverse collection of benchmark classification tasks. Notably, CAMS requires substantially less labeling effort (less than 10%) compared to existing methods on CIFAR10 and DRIFT benchmarks, while achieving similar or better accuracy. 

Large language models (LLMs) are notoriously memory-intensive during training, particularly with the popular AdamW optimizer. This memory burden necessitates using more or higher-end GPUs or reducing batch sizes, limiting training scalability and throughput. To address this, various memory-efficient optimizers have been proposed to reduce optimizer memory usage. However, they face critical challenges: (i) reliance on costly SVD operations; (ii) significant performance trade-offs compared to AdamW; and (iii) still substantial optimizer memory overhead to maintain competitive performance. In this work, we identify that AdamW's learning rate adaptation rule can be effectively coarsened as a structured learning rate update. Based on this insight, we propose Approximated Gradient Scaling for Memory-Efficient LLM Optimization (APOLLO), which approximates learning rate scaling using an auxiliary low-rank optimizer state based on pure random projection. This structured learning rate update rule makes APOLLO highly tolerant to further memory reductions while delivering comparable pre-training performance. Even its rank-1 variant, APOLLO-Mini, achieves superior pre-training performance compared to AdamW with SGD-level memory costs. Extensive experiments demonstrate that the APOLLO series performs on-par with or better than AdamW, while achieving greater memory savings by nearly eliminating the optimization states of AdamW. These savings provide significant system-level benefits: (1) Enhanced Throughput: 3x throughput on an 8xA100-80GB setup compared to AdamW by supporting 4x larger batch sizes. (2) Improved Model Scalability: Pre-training LLaMA-13B with naive DDP on A100-80GB GPUs without system-level optimizations. (3) Low-End GPU Friendly Pre-training: Pre-training LLaMA-7B on a single GPU using less than 12 GB of memory with weight quantization. 

Finetuned large language models (LLMs) have shown remarkable performance in financial tasks, such as sentiment analysis and information retrieval. Due to privacy concerns, finetuning and deploying financial LLMs (FinLLMs) locally are crucial for institutions and individuals. In this paper, we employ quantized low-rank adaptation (QLoRA) to finetune FinLLMs, which leverage low-rank structure and quantization technique to significantly reduce computational requirements while maintaining model performance. We also employ data and pipeline parallelism to enable local finetuning on commodity GPUs. Experiments on financial datasets validate the efficacy of our approach in yielding notable improvements over the base models.