From $\log π$ to $π$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
Fuente:
arXiv
Saved in:
| Main Authors: | Fu, Xiaoliang, Lin, Jiaye, Fang, Yangyi, Hu, Chaowen, Qin, Cong, Shao, Zekai, Zheng, Binbin, Pan, Lu, Zeng, Ke |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
by: Fu, Xiaoliang, et al.
Published: (2026)
by: Fu, Xiaoliang, et al.
Published: (2026)
How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
by: Fang, Yangyi, et al.
Published: (2026)
by: Fang, Yangyi, et al.
Published: (2026)
Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning
by: Fang, Yangyi, et al.
Published: (2026)
by: Fang, Yangyi, et al.
Published: (2026)
Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training
by: Fang, Yangyi, et al.
Published: (2026)
by: Fang, Yangyi, et al.
Published: (2026)
Amplitude Analysis of the Decays $D^0\toπ^+π^-π^+π^-$ and $π^+π^-π^0π^0$
by: BESIII Collaboration, et al.
Published: (2023)
by: BESIII Collaboration, et al.
Published: (2023)
Revisiting $C$ and $CP$ Violation in $η\to π^+π^-π^0$ Decay
by: Shi, Jun, et al.
Published: (2024)
by: Shi, Jun, et al.
Published: (2024)
Study of the Decay $D^{+}_{s}\rightarrow π^{+}π^{+}π^{-}η$ and Observation of the W-annihilation Decay $D^{+}_{s}\rightarrow a_0(980)^+ρ^0$
by: Ablikim, M., et al.
Published: (2021)
by: Ablikim, M., et al.
Published: (2021)
Weights for $π$-partial characters of $π$-separable groups
by: Chang, Xuewu, et al.
Published: (2024)
by: Chang, Xuewu, et al.
Published: (2024)
To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
by: Marshall, Noah, et al.
Published: (2024)
by: Marshall, Noah, et al.
Published: (2024)
First Observation of \boldmath{$D^+ \to a_0(980)ρ$ and $D^+ \to a_0(980)^+ f_0(500)$} in \boldmath{$D^+ \to π^+π^+π^-η$ and $D^+ \to π^+π^0π^0η$} Decays
by: BESIII Collaboration, et al.
Published: (2026)
by: BESIII Collaboration, et al.
Published: (2026)
Correction of Decoupled Weight Decay
by: Chou, Jason Chuan-Chih
Published: (2025)
by: Chou, Jason Chuan-Chih
Published: (2025)
The $η/η' \rightarrow π^+ π^- γ$ Decays within BHLS$_2$ and the Muon HVP
by: Benayoun, Maurice, et al.
Published: (2023)
by: Benayoun, Maurice, et al.
Published: (2023)
Monte Carlo Simulation-Based Partial Wave Analysis of $Ξ_c^+ \to Ξ^-π^+π^+$ Decay
by: Li, S. X., et al.
Published: (2025)
by: Li, S. X., et al.
Published: (2025)
Observation of $\barΛp\to K^{+}π^{+}π^{-}π^{0}$ and $\barΛp\to K^{+}π^{+}π^{-}2π^{0}$
by: BESIII Collaboration, et al.
Published: (2026)
by: BESIII Collaboration, et al.
Published: (2026)
Study of the reactions $\bar{n} p \to 2π^{+}π^{-}$, $2π^{+}π^{-}π^{0}$, and $2π^{+}π^{-}2π^{0}$ using $J/ψ\to p π^{-}\bar{n}$
by: BESIII Collaboration, et al.
Published: (2025)
by: BESIII Collaboration, et al.
Published: (2025)
Mitigating Voltage Decay via Chemo‐Mechanical Decoupling Enabled by a Rigid‐Soft Gradient Interphase in Li‐Rich Layered Oxides
by: Lingcai Zeng, et al.
Published: (2026)
by: Lingcai Zeng, et al.
Published: (2026)
Quasi-Two-Body $B\to P (K^+K^-, π^+π^-)$ Decays with $f_0(980)$ Resonance
by: Wang, Ya-Xin, et al.
Published: (2025)
by: Wang, Ya-Xin, et al.
Published: (2025)
Measurements of branching fractions of $D^0\to K^- 3π^+2π^-$, $D^0\to K^- 2π^+π^-2π^0$ and $D^+\to K^- 3π^+π^-π^0$
by: BESIII Collaboration, et al.
Published: (2025)
by: BESIII Collaboration, et al.
Published: (2025)
Cross Section Measurements of $\bar{n}p \rightarrow K^{+}K^{-}π^{+}(π^{0})$ via Antineutrons Produced by $J/ψ\to p π^{-} \bar{n}$ Decays
by: BESIII Collaboration, et al.
Published: (2026)
by: BESIII Collaboration, et al.
Published: (2026)
Measurement of the branching fractions of $D^+ \to K^+K^-π^+π^+π^-$, $ϕπ^+π^+π^-$, $K^0_SK^+π^+π^-π^0$, $K^0_SK^+η$, and $K^0_SK^+ω$ decays
by: BESIII Collaboration, et al.
Published: (2025)
by: BESIII Collaboration, et al.
Published: (2025)
Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate
by: Xu, Huangyu, et al.
Published: (2026)
by: Xu, Huangyu, et al.
Published: (2026)
SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
by: Zheng, Binbin, et al.
Published: (2026)
by: Zheng, Binbin, et al.
Published: (2026)
DP-AdamW: Investigating Decoupled Weight Decay and Bias Correction in Private Deep Learning
by: Chooi, Jay, et al.
Published: (2025)
by: Chooi, Jay, et al.
Published: (2025)
Improved measurement of the decays $η' \to π^{+}π^{-}π^{+(0)}π^{-(0)}$ and search for the rare decay $η' \to 4π^{0}$
by: BESIII Collaboration, et al.
Published: (2023)
by: BESIII Collaboration, et al.
Published: (2023)
Decoupled Weight Decay for Any $p$ Norm
by: Outmezguine, Nadav Joseph, et al.
Published: (2024)
by: Outmezguine, Nadav Joseph, et al.
Published: (2024)
Study of the $f_{0}(980)$ and $f_{0}(500)$ Scalar Mesons through the Decay $D_{s}^{+} \to π^{+} π^{-} e^{+} ν_{e}$
by: BESIII Collaboration, et al.
Published: (2023)
by: BESIII Collaboration, et al.
Published: (2023)
Observation of the decay $h_{c}\to3(π^{+}π^{-})π^{0}$
by: BESIII Collaboration, et al.
Published: (2024)
by: BESIII Collaboration, et al.
Published: (2024)
Observation of the $W$-annihilation process $D_s^+ \to ωρ^+$ and measurement of $D_s^+ \to ϕρ^+$ in $D^+_s\to π^+π^+π^-π^0π^0$ decays
by: BESIII Collaboration, et al.
Published: (2025)
by: BESIII Collaboration, et al.
Published: (2025)
Online Distributed Optimization with Clipped Stochastic Gradients: High Probability Bound of Regrets
by: Yang, Yuchen, et al.
Published: (2024)
by: Yang, Yuchen, et al.
Published: (2024)
Observation of $D \to a_{0}(980)π$ in the decays $D^{0} \rightarrow π^{+}π^{-}η$ and $D^{+} \rightarrow π^{+}π^{0}η$
by: BESIII Collaboration, et al.
Published: (2024)
by: BESIII Collaboration, et al.
Published: (2024)
Standard Model Benchmarks for $D^0\to K^- K^+, π^-π^+, K^0_{\rm S} K^0_{\rm S}$ Decays
by: Fleischer, Robert, et al.
Published: (2025)
by: Fleischer, Robert, et al.
Published: (2025)
Study of the $B^{+}\toπ^{+}\left(π^{+}π^{-}\right)$ decay in PQCD Approach
by: Chang, Qin, et al.
Published: (2024)
by: Chang, Qin, et al.
Published: (2024)
It's Not You, It's Clipping: A Soft Trust-Region via Probability Smoothing for LLM RL
by: Dwyer, Madeleine, et al.
Published: (2025)
by: Dwyer, Madeleine, et al.
Published: (2025)
Observation of a threshold enhancement in the $π^+π^-$ spectrum in $ψ(3686) \rightarrow π^{+}π^{-}J/ψ$ decays
by: BESIII Collaboration, et al.
Published: (2025)
by: BESIII Collaboration, et al.
Published: (2025)
Search for $η_c(2S)\to 2(π^+π^-)$ and improved measurement of $χ_{cJ}\to 2(π^+π^-)$
by: BESIII Collaboration, et al.
Published: (2024)
by: BESIII Collaboration, et al.
Published: (2024)
Observation of the Singly Cabibbo-Suppressed Decay $Λ_{c}^{+}\to Σ^{-}K^{+}π^{+}$
by: BESIII Collaboration, et al.
Published: (2023)
by: BESIII Collaboration, et al.
Published: (2023)
Observation of new baryons in the $Ξ_b^-π^+π^-$ and $Ξ_b^0π^+π^-$ systems
by: LHCb collaboration, et al.
Published: (2023)
by: LHCb collaboration, et al.
Published: (2023)
Amplitude Analysis and Branching Fraction Measurement of $D^+ \to π^+π^0π^0$
by: BESIII Collaboration, et al.
Published: (2025)
by: BESIII Collaboration, et al.
Published: (2025)
Study of $D_{s1}(2460)^{+}\to D_{s}^{+}π^{+}π^{-}$ in $B\to {\bar{D}}^{(*)}D_{s}^{+}π^{+}π^{-}$ decays
by: LHCb collaboration, et al.
Published: (2024)
by: LHCb collaboration, et al.
Published: (2024)
Light Out‐Coupling for High‐Performance Quantum Dot Light‐Emitting Diodes by π‐π Oriented PEDOT: PSS
by: Yaolong Zhao, et al.
Published: (2024)
by: Yaolong Zhao, et al.
Published: (2024)
Similar Items
-
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
by: Fu, Xiaoliang, et al.
Published: (2026) -
How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
by: Fang, Yangyi, et al.
Published: (2026) -
Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning
by: Fang, Yangyi, et al.
Published: (2026) -
Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training
by: Fang, Yangyi, et al.
Published: (2026) -
Amplitude Analysis of the Decays $D^0\toπ^+π^-π^+π^-$ and $π^+π^-π^0π^0$
by: BESIII Collaboration, et al.
Published: (2023)