AF: Large: Collaborative Research: Nonconvex Methods and Models for Learning: Toward Algorithms with Provable and Interpretable Guarantees

AF:大型:协作研究:非凸学习方法和模型:具有可证明和可解释保证的算法

基本信息

  • 批准号:
    1704860
  • 负责人:
  • 金额:
    $ 170万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2017
  • 资助国家:
    美国
  • 起止时间:
    2017-06-01 至 2023-05-31
  • 项目状态:
    已结题

项目摘要

Artificial Intelligence along with Machine Learning are perhaps the most dominant research themes of our times - with far reaching implications for society and our current life style. While the possibilities are many, there are also doubts about how far these methods will go - and what new theoretical foundations may be required to take them to the next level overcoming possible hurdles. Recently, machine learning has undergone a paradigm shift with increasing reliance on stochastic optimization to train highly non-convex models -- including but not limited to deep nets. Theoretical understanding has lagged behind, primarily because most problems in question are provably intractable on worst-case instances. Furthermore, traditional machine learning theory is mostly concerned with classification, whereas much practical success is driven by unsupervised learning and representation learning. Most past theory of representation learning was focused on simple models such as k-means clustering and PCA, whereas practical work uses vastly more complicated models like autoencoders, restricted Boltzmann machines and deep generative models. The proposal presents an ambitious agenda for extending theory to embrace and support these practical trends, with hope of influencing practice. Theoretical foundations will be provided for the next generation of machine learning methods and optimization algorithms. The project may end up having significant impact on practical machine learning, and even cause a cultural change in the field -- theory as well as practice -- with long-term ramifications. Given the ubiquity as well as economic and scientific implications of machine learning today, such impact will extend into other disciplines, especially in (ongoing) collaborations with researchers in neuroscience. The project will train a new generation of machine learning researchers, through an active teaching and mentoring plan at all levels, from undergrad to postdoc. This new generation will be at ease combining cutting edge theory and applications. There is a pressing need for such people today, and the senior PIs played a role in training/mentoring several existing ones. Technical contributions will include new theoretical models of knowledge representation and semantics, and also frameworks for proving convergence of nonconvex optimization routines. Theory will be developed to explain and exploit the interplay between representation learning and supervised learning that has proved so empirically successful in deep learning, and seems to underlie new learning paradigms such as domain adaptation, transfer learning, and interactive learning. Attempts will be made to replace neural models with models with more "interpretable" attributes and performance curves. All PIs have a track record of combining theory with practice. They are also devoted to a heterodox research approach, borrowing from all the past phases of machine learning: interpretable representations from the earlier phases (which relied on logical representations, or probabilistic models), provable guarantees from the middle phase (convex optimization, kernels etc.), and an embrace of nonconvex methods from the latest deep net phase. Such eclecticism is uncommon in machine learning, and may give rise to new paradigms and new kinds of science.
人工智能沿着机器学习也许是我们这个时代最主要的研究主题-对社会和我们目前的生活方式具有深远的影响。虽然可能性有很多,但人们也怀疑这些方法能走多远,以及可能需要哪些新的理论基础才能将它们提升到一个新的水平,克服可能的障碍。最近,机器学习经历了范式转变,越来越依赖随机优化来训练高度非凸模型,包括但不限于深度网络。理论上的理解已经落后了,主要是因为大多数问题在最坏的情况下都是难以解决的。此外,传统的机器学习理论主要关注分类,而许多实际成功是由无监督学习和表示学习驱动的。大多数过去的表示学习理论都集中在简单的模型上,如k均值聚类和PCA,而实际工作使用更复杂的模型,如自动编码器,受限玻尔兹曼机和深度生成模型。该提案提出了一个雄心勃勃的议程,旨在扩展理论,以拥抱和支持这些实践趋势,并希望影响实践。为下一代机器学习方法和优化算法提供理论基础。该项目最终可能会对实际的机器学习产生重大影响,甚至会引起该领域的文化变革-理论和实践-并产生长期影响。鉴于机器学习的普遍性以及经济和科学影响,这种影响将扩展到其他学科,特别是与神经科学研究人员的(持续)合作。该项目将通过积极的教学和指导计划,培养新一代的机器学习研究人员,从本科到博士后。新一代将轻松结合前沿理论和应用。今天迫切需要这样的人,高级PI在培训/指导几个现有的PI方面发挥了作用。技术贡献将包括知识表示和语义的新理论模型,以及证明非凸优化例程收敛的框架。理论将被开发来解释和利用表征学习和监督学习之间的相互作用,这种相互作用在深度学习中已被证明是如此成功,并且似乎是领域适应,迁移学习和交互式学习等新学习范式的基础。将尝试用具有更多“可解释”属性和性能曲线的模型来取代神经模型。 所有的PI都有将理论与实践相结合的记录。他们还致力于一种非正统的研究方法,借鉴了机器学习的所有过去阶段:早期阶段的可解释表示(依赖于逻辑表示或概率模型),中间阶段的可证明保证(凸优化,内核等),以及对最新深度网络阶段的非凸方法的拥抱。这种折衷主义在机器学习中并不常见,可能会产生新的范式和新的科学类型。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Sanjeev Arora其他文献

Acceso a la asistencia: Manejo de la infección por el virus de la hepatitis C en lugares remotos
获取帮助: 丙型肝炎病毒感染的说明
  • DOI:
  • 发表时间:
    2013
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Sanjeev Arora;Karla Thornton;Andrea Bradford
  • 通讯作者:
    Andrea Bradford
Polynomial time approximation schemes for Euclidean TSP and other geometric problems
Project ECHO for Cancer Care: a Scoping Review of Provider Outcome Evaluations
癌症护理 ECHO 项目:对提供者结果评估的范围审查
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    1.6
  • 作者:
    Sanjeev Arora;Heidi Rishel Brakey;Jessica L Jones;Nancy Hood;Jesus E. Fuentes;Lucca Cirolia
  • 通讯作者:
    Lucca Cirolia
Relativizing versus Nonrelativizing Techniques: The Role of Local Checkability
相对化与非相对化技术:局部可检查性的作用
  • DOI:
    10.1007/s00037-008-0248-y
  • 发表时间:
    1992
  • 期刊:
  • 影响因子:
    1.4
  • 作者:
    Sanjeev Arora;U. C. Berkeley;R. Impagliazzo;U. Diego;U. Vazirani
  • 通讯作者:
    U. Vazirani
Computational Complexity and Information Asymmetry in Financial Products (Extended Abstract)
金融产品中的计算复杂性和信息不对称(扩展摘要)

Sanjeev Arora的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Sanjeev Arora', 18)}}的其他基金

Collaborative Research: RI:Medium:MoDL:Mathematical and Conceptual Understanding of Large Language Models
合作研究:RI:Medium:MoDL:大型语言模型的数学和概念理解
  • 批准号:
    2211779
  • 财政年份:
    2022
  • 资助金额:
    $ 170万
  • 项目类别:
    Standard Grant
AF: Small: Linear Algebra++ and applications to machine learning
AF:小:线性代数及其在机器学习中的应用
  • 批准号:
    1527371
  • 财政年份:
    2015
  • 资助金额:
    $ 170万
  • 项目类别:
    Standard Grant
AF: Medium: Towards Provable Bounds for Machine Learning
AF:中:迈向机器学习的可证明界限
  • 批准号:
    1302518
  • 财政年份:
    2013
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
AF: Small: Expansion, Unique Games, and Efficient Algorithms
AF:小:扩展、独特的游戏和高效的算法
  • 批准号:
    1117309
  • 财政年份:
    2011
  • 资助金额:
    $ 170万
  • 项目类别:
    Standard Grant
New Directions in Semidefinite Programming and Approximation
半定规划和逼近的新方向
  • 批准号:
    0830673
  • 财政年份:
    2008
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
Collaborative Research: Understanding, Coping with, and Benefiting from Intractibility.
合作研究:理解、应对棘手问题并从中受益。
  • 批准号:
    0832797
  • 财政年份:
    2008
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
New directions in Approximation Algorithms for NP-hard problems
NP 难题近似算法的新方向
  • 批准号:
    0514993
  • 财政年份:
    2005
  • 资助金额:
    $ 170万
  • 项目类别:
    Standard Grant
Collaborative Research: MSPA-MCS: Embeddings of Finite Metric Spaces - A Geometric Approach to Efficient Algorithms
合作研究:MSPA-MCS:有限度量空间的嵌入 - 高效算法的几何方法
  • 批准号:
    0528414
  • 财政年份:
    2005
  • 资助金额:
    $ 170万
  • 项目类别:
    Standard Grant
ITR: New directions in clustering and learning
ITR:聚类和学习的新方向
  • 批准号:
    0205594
  • 财政年份:
    2002
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
Approximation of NP-Hard Problems: Algorithms and Complexity
NP 难问题的近似:算法和复杂性
  • 批准号:
    0098180
  • 财政年份:
    2001
  • 资助金额:
    $ 170万
  • 项目类别:
    Standard Grant

相似国自然基金

水稻穗粒数调控关键因子LARGE6的分子遗传网络解析
  • 批准号:
  • 批准年份:
    2022
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
量子自旋液体中拓扑拟粒子的性质:量子蒙特卡罗和新的large-N理论
  • 批准号:
  • 批准年份:
    2020
  • 资助金额:
    62 万元
  • 项目类别:
    面上项目
甘蓝型油菜Large Grain基因调控粒重的分子机制研究
  • 批准号:
    31972875
  • 批准年份:
    2019
  • 资助金额:
    58.0 万元
  • 项目类别:
    面上项目
Large PB/PB小鼠 视网膜新生血管模型的研究
  • 批准号:
    30971650
  • 批准年份:
    2009
  • 资助金额:
    8.0 万元
  • 项目类别:
    面上项目
基因discs large在果蝇卵母细胞的后端定位及其体轴极性形成中的作用机制
  • 批准号:
    30800648
  • 批准年份:
    2008
  • 资助金额:
    20.0 万元
  • 项目类别:
    青年科学基金项目
LARGE基因对口腔癌细胞中α-DG糖基化及表达的分子调控
  • 批准号:
    30772435
  • 批准年份:
    2007
  • 资助金额:
    29.0 万元
  • 项目类别:
    面上项目

相似海外基金

Collaborative Research: AF: Medium: Foundations of Anonymous Communication in Large-Scale Networks
合作研究:AF:媒介:大规模网络中匿名通信的基础
  • 批准号:
    2312241
  • 财政年份:
    2023
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
Collaborative Research: AF: Medium: Foundations of Anonymous Communication in Large-Scale Networks
合作研究:AF:媒介:大规模网络中匿名通信的基础
  • 批准号:
    2312242
  • 财政年份:
    2023
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
Collaborative Research: AF: Medium: Foundations of Anonymous Communication in Large-Scale Networks
合作研究:AF:媒介:大规模网络中匿名通信的基础
  • 批准号:
    2312243
  • 财政年份:
    2023
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
AF: Large: Collaborative Research: Nonconvex Methods and Models for Learning: Towards Algorithms with Provable and Interpretable Guarantees
AF:大型:协作研究:非凸学习方法和模型:走向具有可证明和可解释保证的算法
  • 批准号:
    1704656
  • 财政年份:
    2017
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
AF: Large: Collaborative Research: Algebraic Proof Systems, Convexity, and Algorithms
AF:大型:协作研究:代数证明系统、凸性和算法
  • 批准号:
    1565235
  • 财政年份:
    2016
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
AF: Large: Collaborative Research: Algebraic Proof Systems, Convexity, and Algorithms
AF:大型:协作研究:代数证明系统、凸性和算法
  • 批准号:
    1565264
  • 财政年份:
    2016
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
AF: Medium: Collaborative research: Advanced algorithms and high-performance software for large scale eigenvalue problems
AF:中:协作研究:大规模特征值问题的先进算法和高性能软件
  • 批准号:
    1505970
  • 财政年份:
    2015
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
AF: Large: Collaborative Research: Reliable Quantum Communication and Computation in the Presence of Noise
AF:大型:协作研究:噪声存在下的可靠量子通信和计算
  • 批准号:
    1629809
  • 财政年份:
    2015
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
AF: Medium: Collaborative research: Advanced algorithms and high-performance software for large scale eigenvalue problems
AF:中:协作研究:大规模特征值问题的先进算法和高性能软件
  • 批准号:
    1510010
  • 财政年份:
    2015
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
SHF: AF: Large: Collaborative Research: Parallelism without Concurrency
SHF:AF:大型:协作研究:无并发的并行性
  • 批准号:
    1314590
  • 财政年份:
    2013
  • 资助金额:
    $ 170万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了