相关论文: Efficient Lifelong Model Evaluation in an Era of R…

Linear recurrent neural networks have emerged as efficient alternatives to the original Transformer's softmax attention mechanism, thanks to their highly parallelizable training and constant memory and computation requirements at inference.…

Commonly, AI or machine learning (ML) models are evaluated on benchmark datasets. This practice supports innovative methodological research, but benchmark performance can be poorly correlated with performance in real-world applications -- a…

Formal models are essential to specifying large, complex computer systems and verifying their correctness, but are notoriously expensive to write and maintain. Recent advances in generative AI show promise in generating certain forms of…

Despite being a key bottleneck in many machine learning tasks, the cost of solving large linear systems has proven challenging to quantify due to problem-dependent quantities such as condition numbers. To tackle this, we consider a…

Deep neural networks (DNNs) must cater to a variety of users with different performance needs and budgets, leading to the costly practice of training, storing, and maintaining numerous user/task-specific models. There are solutions in the…

Additive smooth models, such as Generalized additive models (GAMs) of location, scale, and shape (GAMLSS), are a popular choice for modeling experimental data. However, software available to fit such models is usually not tailored…

In this paper, we propose a framework for achieving long-term fair sequential decision making. By conducting both the hard and soft interventions, we propose to take path-specific effects on the time-lagged causal graph as a quantitative…

We propose sequenced-replacement sampling (SRS) for training deep neural networks. The basic idea is to assign a fixed sequence index to each sample in the dataset. Once a mini-batch is randomly drawn in each training iteration, we refill…

In the era of increasingly complex AI models for time series forecasting, progress is often measured by marginal improvements on benchmark leaderboards. However, this approach suffers from a fundamental flaw: standard evaluation metrics…

Large language models (LLMs) are increasingly deployed in real-world systems, yet they can produce toxic or biased outputs that undermine safety and trust. Post-hoc model repair provides a practical remedy, but the high cost of parameter…

Both few-shot and continual learning have seen substantial progress in the last years due to the introduction of proper benchmarks. That being said, the field has still to frame a suite of benchmarks for the highly desirable setting of…

Humans can continuously learn new knowledge. However, machine learning models suffer from drastic dropping in performance on previous tasks after learning new tasks. Cognitive science points out that the competition of similar knowledge is…

Evaluation of foundation models often rely on aggregate scores from benchmarks that lack comprehensive coverage and metadata for a fine-grained evaluation. We introduce a framework for automated benchmark generation. Our framework generates…

We study the problem of recovering an incomplete $m\times n$ matrix of rank $r$ with columns arriving online over time. This is known as the problem of life-long matrix completion, and is widely applied to recommendation system, computer…

We apply methods from randomized numerical linear algebra (RandNLA) to develop improved algorithms for the analysis of large-scale time series data. We first develop a new fast algorithm to estimate the leverage scores of an autoregressive…

Because the choice and tuning of the optimizer affects the speed, and ultimately the performance of deep learning, there is significant past and recent research in this area. Yet, perhaps surprisingly, there is no generally agreed-upon…

Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity. In the recent months, a wide spectrum of efficient, fast Transformers have been proposed to tackle this problem, more often…

We use data on 124 batteries released by Stanford University to first try to solve the binary classification problem of determining if a battery is "good" or "bad" given only the first 5 cycles of data (i.e., will it last longer than a…

This paper addresses the challenges of efficiently fine-tuning large language models (LLMs) by exploring data efficiency and hyperparameter optimization. We investigate the minimum data required for effective fine-tuning and propose a novel…

This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former…