PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
为解决直接偏好优化中因数据噪声和标签模糊导致的问题，提出PLC-DPO方法，通过校准策略参考边界来修正标签，提高学习效率与准确性。
0 citationsRead paper
Selected work
Representative Papers
FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
This work addresses the performance degradation and numerical instability of the Shampoo optimizer, which stem from its reliance on stale preconditioners due to the high computational cost of matrix inversion. The paper provides a theoretical analysis of how delayed preconditioner updates affect convergence and stability, and for the first time explicitly links the damping mechanism to the error induced by such delays. Building on this insight, the authors propose FOAM, an adaptive algorithm that dynamically adjusts both the damping factor and the frequency of eigendecompositions. FOAM further incorporates a delay-aware approximation of the update error, enabling robust convergence while substantially reducing runtime. The method thus achieves an effective balance between computational efficiency and numerical stability.
0 citationsRead paper
Recent publications
Latest Papers
PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
为解决直接偏好优化中因数据噪声和标签模糊导致的问题，提出PLC-DPO方法，通过校准策略参考边界来修正标签，提高学习效率与准确性。
0 citationsRead paper
FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
This work addresses the performance degradation and numerical instability of the Shampoo optimizer, which stem from its reliance on stale preconditioners due to the high computational cost of matrix inversion. The paper provides a theoretical analysis of how delayed preconditioner updates affect convergence and stability, and for the first time explicitly links the damping mechanism to the error induced by such delays. Building on this insight, the authors propose FOAM, an adaptive algorithm that dynamically adjusts both the damping factor and the frequency of eigendecompositions. FOAM further incorporates a delay-aware approximation of the update error, enabling robust convergence while substantially reducing runtime. The method thus achieves an effective balance between computational efficiency and numerical stability.
0 citationsRead paper