Search for: All records

Creators/Authors contains: "Guan, Hui"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Forward-mode automatic differentiation (FmAD) and zero-order (ZO) optimization are increasingly proposed as memory-efficient, backpropagation-free alternatives for large language model (LLM) fine-tuning, yet their benefits are typically evaluated only against standard backpropagation (BP), omitting memory-efficient variants such as activation checkpointing. We present a unified theoretical and empirical comparison of BP, checkpointed BP, FmAD, and ZO for LLM and vision-language model training, showing that while FmAD and ZO reduce activation memory, they trade memory for higher computational cost and longer wall-clock time to convergence, resulting in lower accuracy and slower training, especially under constrained perturbation budgets. Across models, BP with checkpointing outperforms FmAD and ZO variants, including variance-reduced methods, achieving up to 31.1% higher accuracy, 34.8% faster convergence, and 3.8 fewer computations at comparable memory usage, while also revealing instability-related failure modes in FmAD and ZO. Overall, our results correct a one-sided benchmarking narrative by showing that memory-efficient methods entail fundamentally different trade-offs, and that ignoring these distinctions has led to misleading conclusions about LLM optimization in prior work. 
    more » « less
    Free, publicly-accessible full text available July 7, 2027
  2. Free, publicly-accessible full text available July 6, 2027
  3. Free, publicly-accessible full text available May 11, 2027
  4. Free, publicly-accessible full text available May 18, 2027
  5. Free, publicly-accessible full text available December 9, 2026
  6. Free, publicly-accessible full text available February 2, 2027
  7. Free, publicly-accessible full text available December 1, 2026
  8. This work addresses a key challenge in the effective adoption of Recurrent Neural Networks (RNNs) by reducing inference time and expanding the scope of a prediction. It introduces compressed learning, a novel approach that integrates Context-Free Grammar (CFG) and online tokenization into the training and inference of RNNs for streaming inputs. Through a hierarchical compression algorithm, it compresses an input sequence to a CFG and makes predictions based on the compressed sequence. Its algorithm design employs a set of techniques to overcome the issues from the myopic nature of online tokenization, the tension between inference accuracy and compression rate, and other complexities in sequence compression and prediction. Its effectiveness is theoretically analyzed and empirically validated on 16 real-world sequences, including program function calls, memory traces, and system logs. Empirical results demonstrate that compressed learning can successfully recognize and leverage repetitive patterns in input sequences, and effectively translate them into dramatic (1–1,762\(\times\)) inference speedups as well as much (1–7,830\(\times\)) expanded prediction scope, while keeping the inference accuracy satisfactory. 
    more » « less
    Free, publicly-accessible full text available February 28, 2027