This work provides a deterministic dynamic stepsize schedule that accelerates the convergence rate of EG to $\mathcal{O}(T^{-2/3+\varepsilon})$ for any $\varepsilon>0$ and shows that this rate is nearly tight when the extrapolation and update steps of EG use the same stepsize.
Yue Wu, Weiqiang Zheng, Yang Cai et al.· arXiv.org· 0 citations
The authors prove that no instance-independent last-iterate rate exists for the broad algorithmic family and establish strong lower bounds for random iterates and suggest that practitioners should distinguish carefully between the latest strategy, a randomly selected strategy, and the best observed strategy when evalua...
Yang Cai, Gabriele Farina, J. Grand-Clément et al.· Operational Research· 1 citation
Auto-bidding is now widely adopted in online advertising platforms, allowing advertisers to specify high-level campaign objectives--such as maximizing total value subject to a return-on-spend (ROS) constraint--rather than manual per-query bids. A central question in algorithmic mechanism design is characterizing the wo...
Yang Cai, Vineet Gupta, Yan-Chen Jiang et al.· 1 citation
We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for open problems that require exploring multiple competing conjectures, overcoming sub...
Yang Cai, Vineet Gupta, Yan-Chen Jiang et al.· 0 citations
This work proposes a family of symmetric multi-player alignment games and proves that any symmetric Nash equilibrium policy of the $(k+1)-player alignment game achieves the optimal $(k,\frac{k}{k+1})$-robust alignment.
An algorithm is given, requiring no knowledge of the horizon, whose cumulative regret satisfies R_t, whose cumulative regret satisfies 1 + O(\sqrt{\ln \ln n / \ln n})\bigr)\sqrt{t \ln n / 2}$ simultaneously for every $t \ge 1$.
Yang Cai, Vineet Gupta, Yan-Chen Jiang et al.· 2 citations
This work builds on the variable-metric framework of Sakaue et al., adding a self-normalized rank-one update, and replaces the $\log\det$ potential by the trace power $\tr(H^{-1/2})$, which is bounded outright and removes the $\ln T$.
Yang Cai, Anupam Gupta, Vineet Gupta et al.· 3 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
