Arrow Research search

Author name cluster

Jinyan Su

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers
2 author rows

Possible papers

5

RLJ Journal 2025 Journal Article

MixUCB: Enhancing Safe Exploration in Contextual Bandits with Human Oversight

  • Jinyan Su
  • Rohan Banerjee
  • Jiankai Sun
  • Wen Sun
  • Sarah Dean

The integration of AI into high-stakes decision-making domains demands safety and accountability. Traditional contextual bandit algorithms for online and adaptive decision-making must balance exploration and exploitation, posing significant risks when applied to critical environments where exploratory actions can lead to severe consequences. To address these challenges, we propose MixUCB, a flexible human-in-the-loop contextual bandit framework that enhances safe exploration by incorporating human expertise and oversight with machine automation. Based on the model's confidence and the associated risks, MixUCB intelligently determines when to seek human intervention. The reliance on human input gradually reduces as the system learns and gains confidence. Theoretically, we analyze the regret and query complexity in order to rigorously answer the question of when to query. Empirically, we validate the effectiveness through extensive experiments on both synthetic and real-world datasets. Our findings underscore the importance of designing decision-making frameworks that are not only theoretically and technically sound, but also align with societal expectations of accountability and safety. Our experimental code is available at: https://github.com/sdean-group/MixUCB

PDF Details

RLC Conference 2025 Conference Paper

MixUCB: Enhancing Safe Exploration in Contextual Bandits with Human Oversight

  • Jinyan Su
  • Rohan Banerjee
  • Jiankai Sun
  • Wen Sun
  • Sarah Dean

The integration of AI into high-stakes decision-making domains demands safety and accountability. Traditional contextual bandit algorithms for online and adaptive decision-making must balance exploration and exploitation, posing significant risks when applied to critical environments where exploratory actions can lead to severe consequences. To address these challenges, we propose MixUCB, a flexible human-in-the-loop contextual bandit framework that enhances safe exploration by incorporating human expertise and oversight with machine automation. Based on the model's confidence and the associated risks, MixUCB intelligently determines when to seek human intervention. The reliance on human input gradually reduces as the system learns and gains confidence. Theoretically, we analyze the regret and query complexity in order to rigorously answer the question of when to query. Empirically, we validate the effectiveness through extensive experiments on both synthetic and real-world datasets. Our findings underscore the importance of designing decision-making frameworks that are not only theoretically and technically sound, but also align with societal expectations of accountability and safety. Our experimental code is available at: https: //github. com/sdean-group/MixUCB

PDF Details

JMLR Journal 2024 Journal Article

Faster Rates of Differentially Private Stochastic Convex Optimization

  • Jinyan Su
  • Lijie Hu
  • Di Wang

In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) and provide excess population risks for some special classes of functions that are faster than the previous results of general convex and strongly convex functions. In the first part of the paper, we study the case where the population risk function satisfies the Tysbakov Noise Condition (TNC) with some parameter $\theta>1$. Specifically, we first show that under some mild assumptions on the loss functions, there is an algorithm whose output could achieve an upper bound of $\tilde{O}((\frac{1}{\sqrt{n}}+\frac{d}{n\epsilon})^\frac{\theta}{\theta-1}) $ and $\tilde{O}((\frac{1}{\sqrt{n}}+\frac{\sqrt{d\log(1/\delta)}}{n\epsilon})^\frac{\theta}{\theta-1})$ for $\epsilon$-DP and $(\epsilon, \delta)$-DP, respectively when $\theta\geq 2$, where $n$ is the sample size and $d$ is the dimension of the space. Then we address the inefficiency issue, improve the upper bounds by $\text{Poly}(\log n)$ factors and extend to the case where $\theta\geq \bar{\theta}>1$ for some known $\bar{\theta}$. Next, we show that the excess population risk of population functions satisfying TNC with parameter $\theta\geq 2$ is always lower bounded by $\Omega((\frac{d}{n\epsilon})^\frac{\theta}{\theta-1}) $ and $\Omega((\frac{\sqrt{d\log(1/\delta)}}{n\epsilon})^\frac{\theta}{\theta-1})$ for $\epsilon$-DP and $(\epsilon, \delta)$-DP, respectively, which matches our upper bounds. In the second part, we focus on a special case where the population risk function is strongly convex. Unlike the previous studies, here we assume the loss function is non-negative and the optimal value of population risk is sufficiently small. With these additional assumptions, we propose a new method whose output could achieve an upper bound of $O(\frac{d\log(1/\delta)}{n^2\epsilon^2}+\frac{1}{n^{\tau}})$ and $O(\frac{d^2}{n^2\epsilon^2}+\frac{1}{n^{\tau}})$ for any $\tau> 1$ in $(\epsilon,\delta)$-DP and $\epsilon$-DP model respectively if the sample size $n$ is sufficiently large. These results circumvent their corresponding lower bounds in (Feldman et al., 2020) for general strongly convex functions. Finally, we conduct experiments of our new methods on real-world data. Experimental results also provide new insights into established theories. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

PDF Details

ICML Conference 2024 Conference Paper

Learning from Streaming Data when Users Choose

  • Jinyan Su
  • Sarah Dean

In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of the user data to incrementally improve its model. The service providers’ models influence which service the user will choose at the next time step, and the user’s choice, in return, influences the model update, leading to a feedback loop. In this paper, we formalize the above dynamics and develop a simple and efficient decentralized algorithm to locally minimize the overall user loss. Theoretically, we show that our algorithm asymptotically converges to stationary points of of the overall loss almost surely. We also experimentally demonstrate the utility of our algorithm with real world data.

Details

UAI Conference 2023 Conference Paper

Differentially Private Stochastic Convex Optimization in (Non)-Euclidean Space Revisited

  • Jinyan Su
  • Changhong Zhao
  • Di Wang 0015

In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) in Euclidean and general $\ell_p^d$ spaces. Specifically, we focus on three settings that are still far from well understood: (1) DP-SCO over a constrained and bounded (convex) set in Euclidean space; (2) unconstrained DP-SCO in $\ell_p^d$ space; (3) DP-SCO with heavy-tailed data over a constrained and bounded set in $\ell_p^d$ space. For problem (1), for both convex and strongly convex loss functions, we propose methods whose outputs could achieve (expected) excess population risks that are only dependent on the Gaussian width of the constraint set, rather than the dimension of the space. Moreover, we also show the bound for strongly convex functions is optimal up to a logarithmic factor. For problems (2) and (3), we propose several novel algorithms and provide the first theoretical results for both cases when $1<p<2$ and $2\leq p\leq \infty$.

Details
v2026.09.13