PaperHub

Martin Takáč

~Martin_Takáč1

24
论文总数
12.0
年均投稿
5.4
平均评分
接收情况11/24
会议分布
ICLR
17
NeurIPS
5
ICML
2

发表论文 (24 篇)

202519

7.0
4

From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation

ICLR 2025Poster
2.5
4

FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning

ICLR 2025withdrawn
4.8
4

Federated Learning Can Find Friends That Are Advantageous

ICLR 2025Rejected
5.2
5

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

ICLR 2025Rejected
3.0
4

Collaborative and Efficient Personalization with Mixtures of Adaptors

ICLR 2025withdrawn
4.9
4

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

ICML 2025Poster
-

Adaptive Regularized Newton Methods with Inexact Hessian

ICLR 2025withdrawn
6.0
4

SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms

ICLR 2025Rejected
5.5
4

$\texttt{MirrorCheck}$ : Efficient Adversarial Defense for Vision-Language Models

ICLR 2025Rejected
3.0
3

Broadening Discovery through Structural Models: Multimodal Combination of Local and Structural Properties for Predicting Chemical Features.

ICLR 2025withdrawn
7.0
4

Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization

ICLR 2025Poster
7.8
4

$\psi$DAG: Projected Stochastic Approximation Iteration for Linear DAG Structure Learning

NeurIPS 2025Rejected
6.3
4

OPTAMI: Global Superlinear Convergence of High-order Methods

ICLR 2025Poster
4.8
4

$\psi$DAG : Projected Stochastic Approximation Iteration for DAG Structure Learning

ICLR 2025Rejected
6.4
4

Uncovering the Spectral Bias in Diagonal State Space Models

NeurIPS 2025Poster
4.9
4

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed

ICML 2025Poster
6.2
5

Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity

ICLR 2025Poster
5.3
4

Clipping Improves Adam and AdaGrad when the Noise Is Heavy-Tailed

ICLR 2025Rejected
5.0
4

Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation

ICLR 2025withdrawn