arXiv subjects

Mengshi Zhao

Publications and source records attributed to Mengshi Zhao.

4 recordsLinked to original sources

arXiv2026

Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe

Modern federated and streaming learning systems often release intermediate models, so privacy must hold for the full trajectory under adaptive interaction. Motivated by participation privacy, we study single-edit neighboring user streams, where one insertion/deletion shifts all subsequent updates and defeats standard Hamming-neighbor continual-release analyses. We give an auditable modular recipe. A randomized buffering wrapper emits bins of size $[U,2U]$, reducing single-edit streams to a Hamming-style per-bin update stream with explicit backlog/delay guarantees, where $U$ is calibrated by the privacy parameters $(\varepsilon,\delta)$. We then prove a certification theorem identifying when a non-adaptive Hamming-neighbor DP proof for a continual primitive lifts to adaptive inputs: the primitive must use fresh per-round randomness and have a stable one-round privacy profile under common adaptive context. Together, these ingredients yield trajectory-level $(\varepsilon,\delta)$-DP for single-edit streams using standard primitives (e.g., tree prefix sums), with an explicit privacy--latency link via $U$.

cs.CR↗

arXiv2025

DEPO: Dual-Efficiency Preference Optimization for LLM Agents

Recent advances in large language models (LLMs) have greatly improved their reasoning and decision-making abilities when deployed as agents. Richer reasoning, however, often comes at the cost of longer chain of thought (CoT), hampering interaction efficiency in real-world scenarios. Nevertheless, there still lacks systematic definition of LLM agent efficiency, hindering targeted improvements. To this end, we introduce dual-efficiency, comprising (i) step-level efficiency, which minimizes tokens per step, and (ii) trajectory-level efficiency, which minimizes the number of steps to complete a task. Building on this definition, we propose DEPO, a dual-efficiency preference optimization method that jointly rewards succinct responses and fewer action steps. Experiments on WebShop and BabyAI show that DEPO cuts token usage by up to 60.9% and steps by up to 26.9%, while achieving up to a 29.3% improvement in performance. DEPO also generalizes to three out-of-domain math benchmarks and retains its efficiency gains when trained on only 25% of the data. Our project page is at https://opencausalab.github.io/DEPO.

cs.CL↗

arXiv2025

Empirical estimator of diversification quotient

The Diversification Quotient (DQ), introduced by Han et al. (2025), is a recently proposed measure of portfolio diversification that quantifies the reduction in a portfolio's risk-level parameter attributable to diversification. Grounded in a rigorous theoretical framework, DQ effectively captures heavy tails, common shocks, and enhances efficiency in portfolio optimization. This paper further explores the convergence properties and asymptotic normality of empirical DQ estimators based on Value at Risk (VaR) and Expected Shortfall (ES), with explicit calculation of the asymptotic variance. In contrast to the diversification ratio (DR) proposed by Tasche (2007), which may exhibit diverging asymptotic variance due to its lack of location invariance, the DQ estimators demonstrate greater robustness under various distributional settings. We further verify their asymptotic properties under elliptical distributions through simulation, and construct confidence intervals for DQ estimates using AR-GARCH models with a residual-based bootstrap on real financial data. These results establish a solid statistical foundation for applying DQ in financial risk management and decision-making.

q-fin.RM↗

arXiv2023

Privacy Amplification by Iteration for ADMM with (Strongly) Convex Objective Functions

We examine a private ADMM variant for (strongly) convex objectives which is a primal-dual iterative method. Each iteration has a user with a private function used to update the primal variable, masked by Gaussian noise for local privacy, without directly adding noise to the dual variable. Privacy amplification by iteration explores if noises from later iterations can enhance the privacy guarantee when releasing final variables after the last iteration. Cyffers et al. [ICML 2023] explored privacy amplification by iteration for the proximal ADMM variant, where a user's entire private function is accessed and noise is added to the primal variable. In contrast, we examine a private ADMM variant requiring just one gradient access to a user's function, but both primal and dual variables must be passed between successive iterations. To apply Balle et al.'s [NeurIPS 2019] coupling framework to the gradient ADMM variant, we tackle technical challenges with novel ideas. First, we address the non-expansive mapping issue in ADMM iterations by using a customized norm. Second, because the dual variables are not masked with any noise directly, their privacy guarantees are achieved by treating two consecutive noisy ADMM iterations as a Markov operator. Our main result is that the privacy guarantee for the gradient ADMM variant can be amplified proportionally to the number of iterations. For strongly convex objective functions, this amplification exponentially increases with the number of iterations. These amplification results align with the previously studied special case of stochastic gradient descent.

cs.LG↗