LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 124

Search options

  1. Book ; Online: Making Decisions under Outcome Performativity

    Kim, Michael P. / Perdomo, Juan C.

    2022  

    Abstract: Decision-makers often act in response to data-driven predictions, with the goal of achieving favorable outcomes. In such settings, predictions don't passively forecast the future; instead, predictions actively shape the distribution of outcomes they are ... ...

    Abstract Decision-makers often act in response to data-driven predictions, with the goal of achieving favorable outcomes. In such settings, predictions don't passively forecast the future; instead, predictions actively shape the distribution of outcomes they are meant to predict. This performative prediction setting raises new challenges for learning "optimal" decision rules. In particular, existing solution concepts do not address the apparent tension between the goals of forecasting outcomes accurately and steering individuals to achieve desirable outcomes. To contend with this concern, we introduce a new optimality concept -- performative omniprediction -- adapted from the supervised (non-performative) learning setting. A performative omnipredictor is a single predictor that simultaneously encodes the optimal decision rule with respect to many possibly-competing objectives. Our main result demonstrates that efficient performative omnipredictors exist, under a natural restriction of performative prediction, which we call outcome performativity. On a technical level, our results follow by carefully generalizing the notion of outcome indistinguishability to the outcome performative setting. From an appropriate notion of Performative OI, we recover many consequences known to hold in the supervised setting, such as omniprediction and universal adaptability.

    Comment: full version of conference paper appearing in ITCS 2023
    Keywords Computer Science - Machine Learning ; Computer Science - Computers and Society ; Statistics - Machine Learning
    Subject code 006
    Publishing date 2022-10-04
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Book ; Online: Backward baselines

    Hardt, Moritz / Kim, Michael P.

    Is your model predicting the past?

    2022  

    Abstract: When does a machine learning model predict the future of individuals and when does it recite patterns that predate the individuals? In this work, we propose a distinction between these two pathways of prediction, supported by theoretical, empirical, and ... ...

    Abstract When does a machine learning model predict the future of individuals and when does it recite patterns that predate the individuals? In this work, we propose a distinction between these two pathways of prediction, supported by theoretical, empirical, and normative arguments. At the center of our proposal is a family of simple and efficient statistical tests, called backward baselines, that demonstrate if, and to which extent, a model recounts the past. Our statistical theory provides guidance for interpreting backward baselines, establishing equivalences between different baselines and familiar statistical concepts. Concretely, we derive a meaningful backward baseline for auditing a prediction system as a black box, given only background variables and the system's predictions. Empirically, we evaluate the framework on different prediction tasks derived from longitudinal panel surveys, demonstrating the ease and effectiveness of incorporating backward baselines into the practice of machine learning.
    Keywords Computer Science - Machine Learning ; Statistics - Machine Learning
    Subject code 006
    Publishing date 2022-06-23
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Book ; Online: Characterizing notions of omniprediction via multicalibration

    Gopalan, Parikshit / Kim, Michael P. / Reingold, Omer

    2023  

    Abstract: A recent line of work shows that notions of multigroup fairness imply surprisingly strong notions of omniprediction: loss minimization guarantees that apply not just for a specific loss function, but for any loss belonging to a large family of losses. ... ...

    Abstract A recent line of work shows that notions of multigroup fairness imply surprisingly strong notions of omniprediction: loss minimization guarantees that apply not just for a specific loss function, but for any loss belonging to a large family of losses. While prior work has derived various notions of omniprediction from multigroup fairness guarantees of varying strength, it was unknown whether the connection goes in both directions. In this work, we answer this question in the affirmative, establishing equivalences between notions of multicalibration and omniprediction. The new definitions that hold the key to this equivalence are new notions of swap omniprediction, which are inspired by swap regret in online learning. We show that these can be characterized exactly by a strengthening of multicalibration that we refer to as swap multicalibration. One can go from standard to swap multicalibration by a simple discretization; moreover all known algorithms for standard multicalibration in fact give swap multicalibration. In the context of omniprediction though, introducing the notion of swapping results in provably stronger notions, which require a predictor to minimize expected loss at least as well as an adaptive adversary who can choose both the loss function and hypothesis based on the value predicted by the predictor. Building on these characterizations, we paint a complete picture of the relationship between the various omniprediction notions in the literature by establishing implications and separations between them. Our work deepens our understanding of the connections between multigroup fairness, loss minimization and outcome indistinguishability and establishes new connections to classic notions in online learning.
    Keywords Computer Science - Machine Learning ; 68T05 ; 68Q32
    Subject code 006
    Publishing date 2023-02-13
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Article ; Online: Mutant p53 partners in crime.

    Kim, Michael P / Lozano, Guillermina

    Cell death and differentiation

    2018  Volume 25, Issue 1, Page(s) 161–168

    Abstract: Mutant p53 proteins impart changes in cellular behavior and function through interactions with proteins that alter gene expression. The milieu of intracellular proteins available to interact with mutant p53 is context specific and changes with disease, ... ...

    Abstract Mutant p53 proteins impart changes in cellular behavior and function through interactions with proteins that alter gene expression. The milieu of intracellular proteins available to interact with mutant p53 is context specific and changes with disease, cell type, and environmental conditions. Varying conformations of mutant p53 largely dictate protein-protein interactions as different point mutations within protein-coding regions greatly alter the extent and array of gain-of-function (GOF) activities. Given such variables, how can knowledge regarding p53 missense mutations be translated into predicting or altering biologic activity for therapy? How may knowledge regarding mutant p53 functions within certain disease contexts be harnessed to blunt or ablate mutant p53 GOF for therapy? In this article, we review known proteins that interact with mutant p53 and result in the activation of genes that contribute to p53 GOF with particular emphasis on context dependency and an evolving appreciation of GOF mechanisms.
    MeSH term(s) Gain of Function Mutation ; Humans ; Mutation, Missense ; Neoplasms/genetics ; Neoplasms/metabolism ; Transcription Factors/metabolism ; Transcriptional Activation ; Tumor Suppressor Protein p53/genetics ; Tumor Suppressor Protein p53/metabolism
    Chemical Substances TP53 protein, human ; Transcription Factors ; Tumor Suppressor Protein p53
    Language English
    Publishing date 2018
    Publishing country England
    Document type Journal Article ; Review
    ZDB-ID 1225672-9
    ISSN 1476-5403 ; 1350-9047
    ISSN (online) 1476-5403
    ISSN 1350-9047
    DOI 10.1038/cdd.2017.185
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 4230: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (2.OG)
    ab Jg. 2022: Lesesaal (EG)
    Zs.MG 80: Show issues

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  5. Article ; Online: Universal adaptability: Target-independent inference that competes with propensity scoring.

    Kim, Michael P / Kern, Christoph / Goldwasser, Shafi / Kreuter, Frauke / Reingold, Omer

    Proceedings of the National Academy of Sciences of the United States of America

    2022  Volume 119, Issue 4

    Abstract: The gold-standard approaches for gleaning statistically valid conclusions from data involve random sampling from the population. Collecting properly randomized data, however, can be challenging, so modern statistical methods, including propensity score ... ...

    Abstract The gold-standard approaches for gleaning statistically valid conclusions from data involve random sampling from the population. Collecting properly randomized data, however, can be challenging, so modern statistical methods, including propensity score reweighting, aim to enable valid inferences when random sampling is not feasible. We put forth an approach for making inferences based on available data from a source population that may differ in composition in unknown ways from an eventual target population. Whereas propensity scoring requires a separate estimation procedure for each different target population, we show how to build a single estimator, based on source data alone, that allows for efficient and accurate estimates on any downstream target data. We demonstrate, theoretically and empirically, that our target-independent approach to inference, which we dub "universal adaptability," is competitive with target-specific approaches that rely on propensity scoring. Our approach builds on a surprising connection between the problem of inferences in unspecified target populations and the multicalibration problem, studied in the burgeoning field of algorithmic fairness. We show how the multicalibration framework can be employed to yield valid inferences from a single source population across a diverse set of target populations.
    Language English
    Publishing date 2022-01-19
    Publishing country United States
    Document type Journal Article ; Research Support, U.S. Gov't, Non-P.H.S. ; Research Support, Non-U.S. Gov't
    ZDB-ID 209104-5
    ISSN 1091-6490 ; 0027-8424
    ISSN (online) 1091-6490
    ISSN 0027-8424
    DOI 10.1073/pnas.2108097119
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 1148: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (1.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  6. Article ; Online: Bacterial and fungal characterization of pancreatic adenocarcinoma from Endoscopic Ultrasound-guided biopsies.

    Wright, Robin D / Bartelli, Thais F / Baydogan, Seyda / White, James Robert / Kim, Michael P / Bhutani, Manoop S / McAllister, Florencia

    Frontiers in immunology

    2023  Volume 14, Page(s) 1268376

    Abstract: Introduction: The tumor microbiome (TM) has been linked to pancreatic cancer prognosis. Specific microbes can confer tumor resistance to therapies. Early knowledge of the TM at time of diagnosis would be clinically relevant for precision therapy based ... ...

    Abstract Introduction: The tumor microbiome (TM) has been linked to pancreatic cancer prognosis. Specific microbes can confer tumor resistance to therapies. Early knowledge of the TM at time of diagnosis would be clinically relevant for precision therapy based on microbial composition. However, it is difficult to define the TM prior to surgical resection.
    Methods: In this pilot feasibility study, patients underwent Endoscopic Ultrasound-Fine Needle Aspiration (EUS-FNA) biopsy of pancreatic adenocarcinoma. These samples were analyzed using 16S rRNA and internal transcribed spacer (ITS) sequencing for characterization of the tumor bacteria and fungi.
    Result: After in silico decontamination and comparison to non-matched tumor, we were able to characterize the TM in biopsies, which was comparable to the TM from surgical specimens.
    Discussion: EUS-FNA biopsy may represent a feasible modality to characterize the pancreatic TM prior to surgical resection with proper decontamination strategies and improvements in matched controls.
    MeSH term(s) Humans ; Pancreatic Neoplasms/pathology ; Adenocarcinoma/diagnostic imaging ; RNA, Ribosomal, 16S/genetics ; Endoscopic Ultrasound-Guided Fine Needle Aspiration ; Bacteria
    Chemical Substances RNA, Ribosomal, 16S
    Language English
    Publishing date 2023-10-13
    Publishing country Switzerland
    Document type Journal Article ; Research Support, N.I.H., Extramural ; Research Support, Non-U.S. Gov't
    ZDB-ID 2606827-8
    ISSN 1664-3224 ; 1664-3224
    ISSN (online) 1664-3224
    ISSN 1664-3224
    DOI 10.3389/fimmu.2023.1268376
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  7. Article ; Online: Transmesocolic Approach for Robotic Duodenal Operations.

    Hirata, Yuki / Maxwell, Jessica E / Kim, Michael P / Tzeng, Ching-Wei D / Katz, Matthew H G / Ikoma, Naruhiko

    Annals of surgical oncology

    2023  Volume 30, Issue 5, Page(s) 2959

    MeSH term(s) Humans ; Robotic Surgical Procedures ; Duodenum/surgery ; Robotics ; Digestive System Surgical Procedures ; Laparoscopy
    Language English
    Publishing date 2023-02-08
    Publishing country United States
    Document type Journal Article
    ZDB-ID 1200469-8
    ISSN 1534-4681 ; 1068-9265
    ISSN (online) 1534-4681
    ISSN 1068-9265
    DOI 10.1245/s10434-023-13178-z
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 4042: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (2.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  8. Book ; Online: Low-Degree Multicalibration

    Gopalan, Parikshit / Kim, Michael P. / Singhal, Mihir / Zhao, Shengjia

    2022  

    Abstract: Introduced as a notion of algorithmic fairness, multicalibration has proved to be a powerful and versatile concept with implications far beyond its original intent. This stringent notion -- that predictions be well-calibrated across a rich class of ... ...

    Abstract Introduced as a notion of algorithmic fairness, multicalibration has proved to be a powerful and versatile concept with implications far beyond its original intent. This stringent notion -- that predictions be well-calibrated across a rich class of intersecting subpopulations -- provides its strong guarantees at a cost: the computational and sample complexity of learning multicalibrated predictors are high, and grow exponentially with the number of class labels. In contrast, the relaxed notion of multiaccuracy can be achieved more efficiently, yet many of the most desirable properties of multicalibration cannot be guaranteed assuming multiaccuracy alone. This tension raises a key question: Can we learn predictors with multicalibration-style guarantees at a cost commensurate with multiaccuracy? In this work, we define and initiate the study of Low-Degree Multicalibration. Low-Degree Multicalibration defines a hierarchy of increasingly-powerful multi-group fairness notions that spans multiaccuracy and the original formulation of multicalibration at the extremes. Our main technical contribution demonstrates that key properties of multicalibration, related to fairness and accuracy, actually manifest as low-degree properties. Importantly, we show that low-degree multicalibration can be significantly more efficient than full multicalibration. In the multi-class setting, the sample complexity to achieve low-degree multicalibration improves exponentially (in the number of classes) over full multicalibration. Our work presents compelling evidence that low-degree multicalibration represents a sweet spot, pairing computational and sample efficiency with strong fairness and accuracy guarantees.

    Comment: Appears at COLT'22
    Keywords Computer Science - Machine Learning ; Computer Science - Computational Complexity
    Subject code 006
    Publishing date 2022-03-02
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  9. Book ; Online: Planting Undetectable Backdoors in Machine Learning Models

    Goldwasser, Shafi / Kim, Michael P. / Vaikuntanathan, Vinod / Zamir, Or

    2022  

    Abstract: Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant an undetectable backdoor into a classifier. On the ... ...

    Abstract Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant an undetectable backdoor into a classifier. On the surface, such a backdoored classifier behaves normally, but in reality, the learner maintains a mechanism for changing the classification of any input, with only a slight perturbation. Importantly, without the appropriate "backdoor key", the mechanism is hidden and cannot be detected by any computationally-bounded observer. We demonstrate two frameworks for planting undetectable backdoors, with incomparable guarantees. First, we show how to plant a backdoor in any model, using digital signature schemes. The construction guarantees that given black-box access to the original model and the backdoored version, it is computationally infeasible to find even a single input where they differ. This property implies that the backdoored model has generalization error comparable with the original model. Second, we demonstrate how to insert undetectable backdoors in models trained using the Random Fourier Features (RFF) learning paradigm or in Random ReLU networks. In this construction, undetectability holds against powerful white-box distinguishers: given a complete description of the network and the training data, no efficient distinguisher can guess whether the model is "clean" or contains a backdoor. Our construction of undetectable backdoors also sheds light on the related issue of robustness to adversarial examples. In particular, our construction can produce a classifier that is indistinguishable from an "adversarially robust" classifier, but where every input has an adversarial example! In summary, the existence of undetectable backdoors represent a significant theoretical roadblock to certifying adversarial robustness.
    Keywords Computer Science - Machine Learning ; Computer Science - Cryptography and Security
    Subject code 006
    Publishing date 2022-04-14
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  10. Article ; Online: Perioperative Therapy for Borderline Resectable Pancreatic Cancer: What and When?

    Kim, Michael P / Katz, Matthew H G

    Annals of surgical oncology

    2019  Volume 26, Issue 6, Page(s) 1596–1597

    MeSH term(s) Antineoplastic Combined Chemotherapy Protocols/therapeutic use ; Humans ; Neoadjuvant Therapy/mortality ; Pancreatectomy/mortality ; Pancreatic Neoplasms/drug therapy ; Pancreatic Neoplasms/pathology ; Pancreatic Neoplasms/surgery ; Perioperative Care/mortality ; Prognosis ; Survival Rate
    Language English
    Publishing date 2019-01-24
    Publishing country United States
    Document type Editorial
    ZDB-ID 1200469-8
    ISSN 1534-4681 ; 1068-9265
    ISSN (online) 1534-4681
    ISSN 1068-9265
    DOI 10.1245/s10434-019-07177-2
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 4042: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (2.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

To top