LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 9 of total 9

Search options

  1. Book ; Online: PAC Verification of Statistical Algorithms

    Mutreja, Saachi / Shafer, Jonathan

    2022  

    Abstract: Goldwasser et al. (2021) recently proposed the setting of PAC verification, where a hypothesis (machine learning model) that purportedly satisfies the agnostic PAC learning objective is verified using an interactive proof. In this paper we develop this ... ...

    Abstract Goldwasser et al. (2021) recently proposed the setting of PAC verification, where a hypothesis (machine learning model) that purportedly satisfies the agnostic PAC learning objective is verified using an interactive proof. In this paper we develop this notion further in a number of ways. First, we prove a lower bound of $\Omega\left(\sqrt{d}/\varepsilon^2\right)$ i.i.d.\ samples for PAC verification of hypothesis classes of VC dimension $d$. Second, we present a protocol for PAC verification of unions of intervals over $\mathbb{R}$ that improves upon their proposed protocol for that task, and matches our lower bound's dependence on $d$. Third, we introduce a natural generalization of their definition to verification of general statistical algorithms, which is applicable to a wider variety of settings beyond agnostic PAC learning. Showcasing our proposed definition, our final result is a protocol for the verification of statistical query algorithms that satisfy a combinatorial constraint on their queries.
    Keywords Statistics - Machine Learning ; Computer Science - Machine Learning
    Subject code 006
    Publishing date 2022-11-28
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  2. Book ; Online: A Trichotomy for Transductive Online Learning

    Hanneke, Steve / Moran, Shay / Shafer, Jonathan

    2023  

    Abstract: We present new upper and lower bounds on the number of learner mistakes in the `transductive' online learning setting of Ben-David, Kushilevitz and Mansour (1997). This setting is similar to standard online learning, except that the adversary fixes a ... ...

    Abstract We present new upper and lower bounds on the number of learner mistakes in the `transductive' online learning setting of Ben-David, Kushilevitz and Mansour (1997). This setting is similar to standard online learning, except that the adversary fixes a sequence of instances $x_1,\dots,x_n$ to be labeled at the start of the game, and this sequence is known to the learner. Qualitatively, we prove a trichotomy, stating that the minimal number of mistakes made by the learner as $n$ grows can take only one of precisely three possible values: $n$, $\Theta\left(\log (n)\right)$, or $\Theta(1)$. Furthermore, this behavior is determined by a combination of the VC dimension and the Littlestone dimension. Quantitatively, we show a variety of bounds relating the number of mistakes to well-known combinatorial dimensions. In particular, we improve the known lower bound on the constant in the $\Theta(1)$ case from $\Omega\left(\sqrt{\log(d)}\right)$ to $\Omega(\log(d))$ where $d$ is the Littlestone dimension. Finally, we extend our results to cover multiclass classification and the agnostic setting.
    Keywords Computer Science - Machine Learning
    Publishing date 2023-11-10
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  3. Book ; Online: The Bayesian Stability Zoo

    Moran, Shay / Schefler, Hilla / Shafer, Jonathan

    2023  

    Abstract: We show that many definitions of stability found in the learning theory literature are equivalent to one another. We distinguish between two families of definitions of stability: distribution-dependent and distribution-independent Bayesian stability. ... ...

    Abstract We show that many definitions of stability found in the learning theory literature are equivalent to one another. We distinguish between two families of definitions of stability: distribution-dependent and distribution-independent Bayesian stability. Within each family, we establish equivalences between various definitions, encompassing approximate differential privacy, pure differential privacy, replicability, global stability, perfect generalization, TV stability, mutual information stability, KL-divergence stability, and R\'enyi-divergence stability. Along the way, we prove boosting results that enable the amplification of the stability of a learning rule. This work is a step towards a more systematic taxonomy of stability notions in learning theory, which can promote clarity and an improved understanding of an array of stability concepts that have emerged in recent years.

    Comment: v2, minor typo fix
    Keywords Computer Science - Machine Learning
    Publishing date 2023-10-27
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  4. Book ; Online: Fantastic Generalization Measures are Nowhere to be Found

    Gastpar, Michael / Nachum, Ido / Shafer, Jonathan / Weinberger, Thomas

    2023  

    Abstract: We study the notion of a generalization bound being uniformly tight, meaning that the difference between the bound and the population loss is small for all learning algorithms and all population distributions. Numerous generalization bounds have been ... ...

    Abstract We study the notion of a generalization bound being uniformly tight, meaning that the difference between the bound and the population loss is small for all learning algorithms and all population distributions. Numerous generalization bounds have been proposed in the literature as potential explanations for the ability of neural networks to generalize in the overparameterized setting. However, in their paper ``Fantastic Generalization Measures and Where to Find Them,'' Jiang et al. (2020) examine more than a dozen generalization bounds, and show empirically that none of them are uniformly tight. This raises the question of whether uniformly-tight generalization bounds are at all possible in the overparameterized setting. We consider two types of generalization bounds: (1) bounds that may depend on the training set and the learned hypothesis (e.g., margin bounds). We prove mathematically that no such bound can be uniformly tight in the overparameterized setting; (2) bounds that may in addition also depend on the learning algorithm (e.g., stability bounds). For these bounds, we show a trade-off between the algorithm's performance and the bound's tightness. Namely, if the algorithm achieves good accuracy on certain distributions, then no generalization bound can be uniformly tight for it in the overparameterized setting. We explain how these formal results can, in our view, inform research on generalization bounds for neural networks, while stressing that other interpretations of these results are also possible.

    Comment: 34 pages, 1 figure. Minor fix: subsection 6.2 -> section 7
    Keywords Computer Science - Machine Learning ; Computer Science - Neural and Evolutionary Computing ; Statistics - Machine Learning
    Subject code 006
    Publishing date 2023-09-24
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  5. Book ; Online: Fine-Grained Distribution-Dependent Learning Curves

    Bousquet, Olivier / Hanneke, Steve / Moran, Shay / Shafer, Jonathan / Tolstikhin, Ilya

    2022  

    Abstract: Learning curves plot the expected error of a learning algorithm as a function of the number of labeled input samples. They are widely used by machine learning practitioners as a measure of an algorithm's performance, but classic PAC learning theory ... ...

    Abstract Learning curves plot the expected error of a learning algorithm as a function of the number of labeled input samples. They are widely used by machine learning practitioners as a measure of an algorithm's performance, but classic PAC learning theory cannot explain their behavior. In this paper we introduce a new combinatorial characterization called the VCL dimension that improves and refines the recent results of Bousquet et al. (2021). Our characterization sheds new light on the structure of learning curves by providing fine-grained bounds, and showing that for classes with finite VCL, the rate of decay can be decomposed into a linear component that depends only on the hypothesis class and an exponential component that depends also on the target distribution. In particular, the finer nuance of the VCL dimension implies lower bounds that are quantitatively stronger than the bounds of Bousquet et al. (2021) and qualitatively stronger than classic 'no free lunch' lower bounds. The VCL characterization solves an open problem studied by Antos and Lugosi (1998), who asked in what cases such lower bounds exist. As a corollary, we recover their lower bound for half-spaces in $\mathbb{R}^d$, and we do so in a principled way that should be applicable to other cases as well. Finally, to provide another viewpoint on our work and how it compares to traditional PAC learning bounds, we also present an alternative formulation of our results in a language that is closer to the PAC setting.
    Keywords Computer Science - Machine Learning ; Computer Science - Computational Complexity ; Statistics - Machine Learning
    Subject code 006
    Publishing date 2022-08-30
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  6. Article ; Online: Sulforaphane inhibits mitochondrial permeability transition and oxidative stress.

    Greco, Tiffany / Shafer, Jonathan / Fiskum, Gary

    Free radical biology & medicine

    2011  Volume 51, Issue 12, Page(s) 2164–2171

    Abstract: Exposure of mitochondria to oxidative stress and elevated Ca(2+) promotes opening of the mitochondrial permeability transition pore (PTP), resulting in membrane depolarization, uncoupling of oxidative phosphorylation, and potentially cell death. This ... ...

    Abstract Exposure of mitochondria to oxidative stress and elevated Ca(2+) promotes opening of the mitochondrial permeability transition pore (PTP), resulting in membrane depolarization, uncoupling of oxidative phosphorylation, and potentially cell death. This study tested the hypothesis that treatment of rats with sulforaphane (SFP), an activator of the Nrf2 pathway of antioxidant gene expression, increases the resistance of liver mitochondria to redox-regulated PTP opening and elevates mitochondrial levels of antioxidants. Rats were injected with SFP or drug vehicle and liver mitochondria were isolated 40h later. Respiring mitochondria actively accumulated added Ca(2+), which was then released through PTP opening induced by agents that either cause an oxidized shift in the mitochondrial redox state or directly oxidize protein thiol groups. SFP treatment of rats inhibited the rate of pro-oxidant-induced mitochondrial Ca(2+) release and increased expression of the glutathione peroxidase/reductase system, thioredoxin, and malic enzyme. These results are the first to demonstrate that SFP treatment of animals increases liver mitochondrial antioxidant defenses and inhibits redox-sensitive PTP opening. This novel form of preconditioning could protect against a variety of pathologies that include oxidative stress and mitochondrial dysfunction in their etiologies.
    MeSH term(s) Animals ; Calcium/metabolism ; Isothiocyanates ; Male ; Mitochondria, Liver/drug effects ; Mitochondria, Liver/metabolism ; Mitochondrial Membrane Transport Proteins/antagonists & inhibitors ; Mitochondrial Membrane Transport Proteins/metabolism ; Mitochondrial Permeability Transition Pore ; Oxidation-Reduction ; Oxidative Stress/drug effects ; Pyridines/metabolism ; Rats ; Rats, Inbred F344 ; Structure-Activity Relationship ; Thiocyanates/administration & dosage ; Thiocyanates/pharmacology
    Chemical Substances Isothiocyanates ; Mitochondrial Membrane Transport Proteins ; Mitochondrial Permeability Transition Pore ; Pyridines ; Thiocyanates ; sulforaphane (GA49J4310U) ; Calcium (SY7Q814VUP)
    Language English
    Publishing date 2011-09-21
    Publishing country United States
    Document type Journal Article ; Research Support, N.I.H., Extramural
    ZDB-ID 807032-5
    ISSN 1873-4596 ; 0891-5849
    ISSN (online) 1873-4596
    ISSN 0891-5849
    DOI 10.1016/j.freeradbiomed.2011.09.017
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  7. Article: Sulforaphane inhibits mitochondrial permeability transition and oxidative stress

    Greco, Tiffany / Shafer, Jonathan / Fiskum, Gary

    Free radical biology & medicine. 2011 Dec. 15, v. 51, no. 12

    2011  

    Abstract: Exposure of mitochondria to oxidative stress and elevated Ca2+ promotes opening of the mitochondrial permeability transition pore (PTP), resulting in membrane depolarization, uncoupling of oxidative phosphorylation, and potentially cell death. This study ...

    Abstract Exposure of mitochondria to oxidative stress and elevated Ca2+ promotes opening of the mitochondrial permeability transition pore (PTP), resulting in membrane depolarization, uncoupling of oxidative phosphorylation, and potentially cell death. This study tested the hypothesis that treatment of rats with sulforaphane (SFP), an activator of the Nrf2 pathway of antioxidant gene expression, increases the resistance of liver mitochondria to redox-regulated PTP opening and elevates mitochondrial levels of antioxidants. Rats were injected with SFP or drug vehicle and liver mitochondria were isolated 40h later. Respiring mitochondria actively accumulated added Ca2+, which was then released through PTP opening induced by agents that either cause an oxidized shift in the mitochondrial redox state or directly oxidize protein thiol groups. SFP treatment of rats inhibited the rate of pro-oxidant-induced mitochondrial Ca2+ release and increased expression of the glutathione peroxidase/reductase system, thioredoxin, and malic enzyme. These results are the first to demonstrate that SFP treatment of animals increases liver mitochondrial antioxidant defenses and inhibits redox-sensitive PTP opening. This novel form of preconditioning could protect against a variety of pathologies that include oxidative stress and mitochondrial dysfunction in their etiologies.
    Keywords antioxidants ; calcium ; cell death ; drugs ; gene expression ; glutathione peroxidase ; liver ; malic enzyme ; membrane permeability ; mitochondria ; oxidative phosphorylation ; oxidative stress ; rats ; thiols
    Language English
    Dates of publication 2011-1215
    Size p. 2164-2171.
    Publishing place Elsevier Inc.
    Document type Article
    ZDB-ID 807032-5
    ISSN 1873-4596 ; 0891-5849
    ISSN (online) 1873-4596
    ISSN 0891-5849
    DOI 10.1016/j.freeradbiomed.2011.09.017
    Database NAL-Catalogue (AGRICOLA)

    More links

    Kategorien

  8. Article ; Online: Parental satisfaction of child's perioperative care.

    Shafer, Jonathan S / Jenkins, Brooke N / Fortier, Michelle A / Stevenson, Robert S / Hikita, Natasha / Zuk, Jeannie / Gold, Jeffrey I / Golianu, Brenda / Kaplan, Sherrie H / Mayes, Linda / Kain, Zeev N

    Paediatric anaesthesia

    2018  Volume 28, Issue 11, Page(s) 955–962

    Abstract: Background: Satisfaction in the hospital setting is an important component of both hospital funding and patient experience. When it comes to a child's hospital experience, parent satisfaction of their child's perioperative care is also necessary to ... ...

    Abstract Background: Satisfaction in the hospital setting is an important component of both hospital funding and patient experience. When it comes to a child's hospital experience, parent satisfaction of their child's perioperative care is also necessary to understand. However, little research has been conducted on the predictors of this outcome. Therefore, the purpose of this current study was to validate a priori selected predictors for parental satisfaction in their child's perioperative process.
    Methods: Eight hundred and ten pediatric patients who underwent tonsillectomy and adenoidectomy surgery and their parents were included in this study. The primary outcome was assessed using a 21-item parent satisfaction questionnaire resulting in three satisfaction scores: overall care satisfaction, OR/induction satisfaction, and total satisfaction.
    Results: Descriptive statistics and correlational analysis found that sedative-premedication, parental presence at anesthesia induction, child social functioning, parental anxiety, and language were all significant predictors of various components of the satisfaction score. Regression models, however, revealed that only parent anxiety and child social functioning remained significant predictors such that parents who reported lower state anxiety (OR/induction satisfaction: OR = 0.975, 95% CI [0.957, 0.994]; total satisfaction: OR = 0.968, 95% CI [0.943, 0.993]) and who had higher socially functioning children (overall care satisfaction: OR = 1.019, 95% CI [1.005, 1.033]; OR/induction satisfaction: OR = 1.011, 95% CI [1.000, 1.022]) were significantly more satisfied with the perioperative care they received.
    Conclusion: Lower parent anxiety and higher child social functioning were predictive of higher parental satisfaction scores.
    MeSH term(s) Anxiety/psychology ; Child ; Child, Preschool ; Female ; Humans ; Hypnosis, Anesthetic/psychology ; Male ; Parents/psychology ; Patient Satisfaction ; Perioperative Care/psychology
    Language English
    Publishing date 2018-10-30
    Publishing country France
    Document type Journal Article ; Research Support, N.I.H., Extramural
    ZDB-ID 1086049-6
    ISSN 1460-9592 ; 1155-5645
    ISSN (online) 1460-9592
    ISSN 1155-5645
    DOI 10.1111/pan.13496
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  9. Article: Sulforaphane inhibits mitochondrial permeability transition and oxidative stress

    Greco, Tiffany / Shafer, Jonathan / Fiskum, Gary

    Free Radical Biology and Medicine

    Volume v. 51,, Issue no. 1

    Abstract: Exposure of mitochondria to oxidative stress and elevated Ca²⁺ promotes opening of the mitochondrial permeability transition pore (PTP), resulting in membrane depolarization, uncoupling of oxidative phosphorylation, and potentially cell death. This study ...

    Abstract Exposure of mitochondria to oxidative stress and elevated Ca²⁺ promotes opening of the mitochondrial permeability transition pore (PTP), resulting in membrane depolarization, uncoupling of oxidative phosphorylation, and potentially cell death. This study tested the hypothesis that treatment of rats with sulforaphane (SFP), an activator of the Nrf2 pathway of antioxidant gene expression, increases the resistance of liver mitochondria to redox-regulated PTP opening and elevates mitochondrial levels of antioxidants. Rats were injected with SFP or drug vehicle and liver mitochondria were isolated 40h later. Respiring mitochondria actively accumulated added Ca²⁺, which was then released through PTP opening induced by agents that either cause an oxidized shift in the mitochondrial redox state or directly oxidize protein thiol groups. SFP treatment of rats inhibited the rate of pro-oxidant-induced mitochondrial Ca²⁺ release and increased expression of the glutathione peroxidase/reductase system, thioredoxin, and malic enzyme. These results are the first to demonstrate that SFP treatment of animals increases liver mitochondrial antioxidant defenses and inhibits redox-sensitive PTP opening. This novel form of preconditioning could protect against a variety of pathologies that include oxidative stress and mitochondrial dysfunction in their etiologies.
    Keywords calcium ; cell death ; drugs ; malic enzyme ; glutathione peroxidase ; oxidative stress ; mitochondria ; antioxidants ; membrane permeability ; thiols ; liver ; gene expression ; rats ; oxidative phosphorylation
    Language English
    Document type Article
    ISSN 0891-5849
    Database AGRIS - International Information System for the Agricultural Sciences and Technology

    More links

    Kategorien

To top