MiniMax
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
Announce Type: new Abstract: We study fixed-confidence best-action identification (BAI) in stochastic minimax trees. This problem is increasingly relevant in modern AI planning, where deep minimax search and Monte Carlo Tree Search (MCTS) with language model long rollouts face a fundamental tradeoff: heuristic evaluations are cheap but biased, while accurate rollouts are reliable but prohibitively expensive. We propose 2FFS, a two-fidelity tree-search algorithm that brings multi-fidelity...
A Temporal Spatial Minimax Rate for Smoothly-Varying Distributions in Wasserstein Space
arXiv:2606.07325v1 Announce Type: cross Abstract: We study the minimax rate of estimating a future value $\mu_{t_n+h}$ of a curve $t\mapsto\mu_t$ in the $2$-Wasserstein space $\mathcal{P}_2(\mathbb{R}^d)$ from finitely many noisy snapshots of its past, under an adiabatic bound $\|\nabla_t^k v\|\le\varepsilon$ on the $k$-th covariant derivative of the velocity field. Our central result is a unified temporal-spatial minimax lower bound: over regular, locally transport-rich subclasses, every...
MiniMax once led Zhipu in Hong Kong’s AI stock race. How the tables have turned
When Chinese artificial intelligence developers Zhipu AI and MiniMax made their debuts on the Hong Kong stock exchange in January, investors initially saw one as a better bet than the other. Beijing-based Zhipu closed its first trading day on January 8 with a market capitalisation of HK$57.9 billion (US$7.4 billion). A day later, Shanghai-based MiniMax listed at HK$106.7 billion, almost twice as large.
AI firm MiniMax prepares for mainland China listing after shares surge in Hong Kong
MiniMax Group, the Chinese artificial intelligence model company, has officially kicked off plans to sell shares in mainland China. This offers onshore investors access to AI players beyond chipmakers and completes a dual-listing status in addition to Hong Kong. The Shanghai-headquartered company signed an agreement with Citic Securities on Friday, hiring the brokerage to help prepare for a sale of yuan-denominated shares.
MiniMax Plans China IPO as it Eyes Local Rivals Like DeepSeek
The logo for MiniMax Group Inc. Photographer: Raul Ariano/Bloomberg
MiniMax Plans China IPO as it Eyes Local Rivals Like DeepSeek
The logo for MiniMax Group Inc. Photographer: Raul Ariano/Bloomberg
Literature-Guided Minimax Optimization of Virtual Epilepsy Neurostimulation
arXiv:2606.04339v1 Announce Type: new Abstract: Computational models of epilepsy promise patient-specific treatment design, but most optimization workflows still search for parameters that perform well on average. In neuromodulation, this is a weak target: a protocol that improves the mean response can still fail in the patient whose network is least tolerant to stimulation. We present a literature-guided minimax pipeline that couples PubMed-scale hypothesis extraction, The Virtual Brain (TVB)
Minimax optimal differentially private synthetic data for smooth queries
arXiv:2602.01607v3 Announce Type: replace-cross Abstract: Differentially private synthetic data enables the sharing and analysis of sensitive datasets while providing rigorous privacy guarantees for individual contributors. A central challenge is to achieve strong utility guarantees for meaningful downstream analysis. Many existing methods ensure uniform accuracy over broad query classes, such as all Lipschitz functions, but this level of generality often leads to suboptimal rates for...
Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods
Announce Type: cross Abstract: Understanding the generalization performance of over-parameterized neural networks has become a central topic in deep learning theory. While recent advances, particularly works under the Neural Tangent Kernel (NTK) regime, have shed light on the behavior of shallow architectures, the statistical generalization properties of deep neural networks (DNNs), especially in regression tasks, remain far less understood.