Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Vankadara, Leena Chennuru"'
Sharpness Aware Minimization (SAM) enhances performance across various neural architectures and datasets. As models are continually scaled up to improve performance, a rigorous understanding of SAM's scaling behaviour is paramount. To this end, we st
Externí odkaz:
http://arxiv.org/abs/2411.00075
Despite the growing popularity of explainable and interpretable machine learning, there is still surprisingly limited work on inherently interpretable clustering methods. Recently, there has been a surge of interest in explaining the classic k-means
Externí odkaz:
http://arxiv.org/abs/2402.09881
Autor:
Faller, Philipp M., Vankadara, Leena Chennuru, Mastakouri, Atalanti A., Locatello, Francesco, Janzing, Dominik
As causal ground truth is incredibly rare, causal discovery algorithms are commonly only evaluated on simulated data. This is concerning, given that simulations reflect preconceptions about generating processes regarding noise distributions, model cl
Externí odkaz:
http://arxiv.org/abs/2307.09552
If $X,Y,Z$ denote sets of random variables, two different data sources may contain samples from $P_{X,Y}$ and $P_{Y,Z}$, respectively. We argue that causal discovery can help inferring properties of the `unobserved joint distributions' $P_{X,Y,Z}$ or
Externí odkaz:
http://arxiv.org/abs/2305.06894
Regression on observational data can fail to capture a causal relationship in the presence of unobserved confounding. Confounding strength measures this mismatch, but estimating it requires itself additional assumptions. A common assumption is the in
Externí odkaz:
http://arxiv.org/abs/2211.01903
We study the problem of learning causal models from observational data through the lens of interpolation and its counterpart -- regularization. A large volume of recent theoretical, as well as empirical work, suggests that, in highly complex model cl
Externí odkaz:
http://arxiv.org/abs/2202.09054
In recent years, several results in the supervised learning setting suggested that classical statistical learning-theoretic measures, such as VC dimension, do not adequately explain the performance of deep learning models which prompted a slew of wor
Externí odkaz:
http://arxiv.org/abs/2112.03968
Autor:
Vankadara, Leena Chennuru, Faller, Philipp Michael, Hardt, Michaela, Minorics, Lenon, Ghoshdastidar, Debarghya, Janzing, Dominik
Despite the increasing relevance of forecasting methods, causal implications of these algorithms remain largely unexplored. This is concerning considering that, even under simplifying assumptions such as causal sufficiency, the statistical risk of a
Externí odkaz:
http://arxiv.org/abs/2111.09831
Despite the ubiquity of kernel-based clustering, surprisingly few statistical guarantees exist beyond settings that consider strong structural assumptions on the data generation process. In this work, we take a step towards bridging this gap by study
Externí odkaz:
http://arxiv.org/abs/2110.09476
Network-valued data are encountered in a wide range of applications and pose challenges in learning due to their complex structure and absence of vertex correspondence. Typical examples of such problems include classification or grouping of protein s
Externí odkaz:
http://arxiv.org/abs/2110.02722