Fri 6:15 a.m. - 6:30 a.m.
|
Welcome and Opening Remarks
(
Opening Remarks
)
>
SlidesLive Video
|
🔗
|
Fri 6:30 a.m. - 7:15 a.m.
|
Efficient Second-Order Stochastic Methods for Machine Learning
(
Plenary Talk
)
>
SlidesLive Video
|
Donald Goldfarb
🔗
|
Fri 7:15 a.m. - 8:00 a.m.
|
Tensor Methods for Nonconvex Optimization.
(
Plenary Talk
)
>
SlidesLive Video
|
Coralia Cartis
🔗
|
Fri 8:00 a.m. - 8:30 a.m.
|
Coffee Break
(
Coffee Break
)
>
|
🔗
|
Fri 8:00 a.m. - 8:30 a.m.
|
Poster Session I
(
Poster Session
)
>
|
🔗
|
Fri 8:30 a.m. - 8:45 a.m.
|
Quartic Polynomial Sub-problem Solutions in Tensor Methods for Nonconvex Optimization
(
Spotlight Talk
)
>
SlidesLive Video
|
Wenqi Zhu
🔗
|
Fri 8:45 a.m. - 9:00 a.m.
|
PSPS: Preconditioned Stochastic Polyak Step-size method for badly scaled data
(
Spotlight Talk
)
>
SlidesLive Video
|
Farshed Abdukhakimov
🔗
|
Fri 9:00 a.m. - 9:15 a.m.
|
DRSOM: A Dimension Reduced Second-Order Method
(
Spotlight Talk
)
>
SlidesLive Video
|
Chuwen Zhang
🔗
|
Fri 9:15 a.m. - 9:30 a.m.
|
Disentangling the Mechanisms Behind Implicit Regularization in SGD
(
Spotlight Talk
)
>
SlidesLive Video
|
Zachary Novack
🔗
|
Fri 9:30 a.m. - 9:45 a.m.
|
Cubic Regularized Quasi-Newton Methods
(
Spotlight Talk
)
>
SlidesLive Video
|
Klea Ziu
🔗
|
Fri 9:45 a.m. - 10:00 a.m.
|
Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initialization
(
Spotlight Talk
)
>
SlidesLive Video
|
Kabir Chandrasekher
🔗
|
Fri 10:00 a.m. - 11:30 a.m.
|
Lunch Break
(
Lunch Break
)
>
|
🔗
|
Fri 11:30 a.m. - 12:15 p.m.
|
Deterministically Constrained Stochastic Optimization
(
Plenary Talk
)
>
SlidesLive Video
|
Frank E. Curtis
🔗
|
Fri 12:15 p.m. - 1:00 p.m.
|
Low Rank Approximation for Faster Convex Optimization
(
Plenary Talk
)
>
SlidesLive Video
|
Madeleine Udell
🔗
|
Fri 1:00 p.m. - 1:30 p.m.
|
Coffee Break
(
Coffee Break
)
>
|
🔗
|
Fri 1:00 p.m. - 2:00 p.m.
|
Poster Session II
(
Poster Session
)
>
|
🔗
|
Fri 2:00 p.m. - 2:45 p.m.
|
A Fast, Fisher Based Pruning of Transformers without Retraining
(
Plenary Talk
)
>
SlidesLive Video
|
Amir Gholami
🔗
|
Fri 2:45 p.m. - 3:00 p.m.
|
Closing Remarks
(
Closing Remarks
)
>
SlidesLive Video
|
🔗
|
-
|
How Small Amount of Data Sharing Benefits Higher-Order Distributed Optimization and Learning
(
Poster
)
>
|
Mingxi Zhu · Yinyu Ye
🔗
|
-
|
A Stochastic Conjugate Subgradient Algorithm for Kernelized Support Vector Machines: The Evidence
(
Poster
)
>
|
Di Zhang · Suvrajeet Sen
🔗
|
-
|
Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation
(
Poster
)
>
|
Rustem Islamov · Xun Qian · Slavomír Hanzely · Mher Safaryan · Peter Richtarik
🔗
|
-
|
Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems
(
Poster
)
>
|
Yuchen Fang · Sen Na · Mladen Kolar
🔗
|
-
|
Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models: First-Order Stationarity
(
Poster
)
>
|
Yuchen Fang · Sen Na · Mladen Kolar
🔗
|
-
|
Black Box Lie Group Preconditioners for SGD
(
Poster
)
>
|
Xilin Li
🔗
|
-
|
Perseus: A Simple and Optimal High-Order Method for Variational Inequalities
(
Poster
)
>
|
Tianyi Lin · Michael Jordan
🔗
|
-
|
High-Order Optimization of Gradient Boosted Decision Trees
(
Poster
)
>
|
Jean Pachebat · Sergey IVANOV
🔗
|
-
|
On the Global Convergence of the Regularized Generalized Gauss-Newton Algorithm
(
Poster
)
>
|
Vincent Roulet · Maryam Fazel · Siddhartha Srinivasa · Zaid Harchaoui
🔗
|
-
|
Disentangling the Mechanisms Behind Implicit Regularization in SGD
(
Poster
)
>
|
Zachary Novack · Simran Kaur · Tanya Marwah · Saurabh Garg · Zachary Lipton
🔗
|
-
|
Effects of momentum scaling for SGD
(
Poster
)
>
|
Dmitry A. Pasechnyuk · Alexander Gasnikov · Martin Takac
🔗
|
-
|
Using quadratic equations for overparametrized models
(
Poster
)
>
|
Shuang Li · William Swartworth · Martin Takac · Deanna Needell · Robert Gower
🔗
|
-
|
Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initialization
(
Poster
)
>
|
MENGQI LOU · Kabir Chandrasekher · Ashwin Pananjady
🔗
|
-
|
Improving Levenberg-Marquardt Algorithm for Neural Networks
(
Poster
)
>
|
Omead Pooladzandi · Yiming Zhou
🔗
|
-
|
DRSOM: A Dimension Reduced Second-Order Method
(
Poster
)
>
|
Chuwen Zhang · Jiang Bo · Chang He · Yuntian Jiang · Dongdong Ge · Yinyu Ye
🔗
|
-
|
Random-subspace adaptive cubic regularisation method for nonconvex optimisation
(
Poster
)
>
|
Coralia Cartis · Zhen Shao
🔗
|
-
|
Quartic Polynomial Sub-problem Solutions in Tensor Methods for Nonconvex Optimization
(
Poster
)
>
|
Wenqi Zhu · Coralia Cartis
🔗
|
-
|
FLECS-CGD: A Federated Learning Second-Order Framework via Compression and Sketching with Compressed Gradient Differences
(
Poster
)
>
|
Artem Agafonov · Brahim Erraji · Martin Takac
🔗
|
-
|
Statistical and Computational Complexities of BFGS Quasi-Newton Method for Generalized Linear Models
(
Poster
)
>
|
Qiujiang Jin · Aryan Mokhtari · Nhat Ho · Tongzheng Ren
🔗
|
-
|
The Trade-offs of Incremental Linearization Algorithms for Nonsmooth Composite Problems
(
Poster
)
>
|
Krishna Pillutla · Vincent Roulet · Sham Kakade · Zaid Harchaoui
🔗
|
-
|
Cubic Regularized Quasi-Newton Methods
(
Poster
)
>
|
Dmitry Kamzolov · Klea Ziu · Artem Agafonov · Martin Takac
🔗
|
-
|
ASDL: A Unified Interface for Gradient Preconditioning in PyTorch
(
Poster
)
>
|
Kazuki Osawa · Satoki Ishikawa · Rio Yokota · Shigang Li · Torsten Hoefler
🔗
|
-
|
PSPS: Preconditioned Stochastic Polyak Step-size method for badly scaled data
(
Poster
)
>
|
Farshed Abdukhakimov · Chulu Xiang · Dmitry Kamzolov · Robert Gower · Martin Takac
🔗
|
-
|
HesScale: Scalable Computation of Hessian Diagonals
(
Poster
)
>
|
Mohamed Elsayed · Rupam Mahmood
🔗
|