Physical Sciences and Mathematics Commons^™

On Pac Learning Halfspaces In Non-Interactive Local Privacy Model With Public Unlabeled Data, Jinyan Su, Jinhui Xu, Di Wang

Machine Learning Faculty Publications

In this paper, we study the problem of PAC learning halfspaces in the non-interactive local differential privacy model (NLDP). To breach the barrier of exponential sample complexity, previous results studied a relaxed setting where the server has access to some additional public but unlabeled data. We continue in this direction. Specifically, we consider the problem under the standard setting instead of the large margin setting studied before. Under different mild assumptions on the underlying data distribution, we propose two approaches that are based on the Massart noise model and self-supervised learning and show that it is possible to achieve sample …

A Cybersecurity Assessment Of Health Data Ecosystems, Michelle N. Halsey

Cyber Operations and Resilience Program Graduate Projects

This paper is an exploratory study that investigates data collected and used by health plans and reviews the laws and regulations governing this data to identify the gaps in protections and provide recommendations for eliminating these gaps. Health insurance companies collect a wide array of data about the people they insure, data that is often only peripherally relevant to the service these companies provide. The data environment currently consists of seven categories of data: personal health information, summary health information, personally identifiable information, financial information, professional information, biometric information, and lifestyle data or social indicators of health. Much of this …

Experimental Identification Of Aminomethanol (Nh2ch2oh)—The Key Intermediate In The Strecker Synthesis, Santosh K. Singh, Cheng Zhu, Jesse La Jeunesse, Ryan C. Fortenberry, Ralf I. Kaiser

Faculty and Student Publications

The Strecker Synthesis of (a)chiral α-amino acids from simple organic compounds, such as ammonia (NH3), aldehydes (RCHO), and hydrogen cyanide (HCN) has been recognized as a viable route to amino acids on primordial earth. However, preparation and isolation of the simplest hemiaminal intermediate – the aminomethanol (NH2CH2OH)– formed in the Strecker Synthesis to even the simplest amino acid glycine (H2NCH2COOH) has been elusive. Here, we report the identification of aminomethanol prepared in low-temperature methylamine (CH3NH2) – oxygen (O2) ices upon exposure to energetic electrons. Isomer-selective photoionization time-of-flight mass spectrometry (PI-ReTOF-MS) facilitated the gas phase detection of aminomethanol during the temperature …

A Damped Newton Method Achieves Global O(1/K2) And Local Quadratic Convergence Rate, Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander Gasnikov, Peter Richtárik, Martin Takáč

Machine Learning Faculty Publications

In this paper, we present the first stepsize schedule for Newton method resulting in fast global and local convergence guarantees. In particular, a) we prove an O (1/k2) global rate, which matches the state-of-the-art global rate of cubically regularized Newton method of Polyak and Nesterov (2006) and of regularized Newton method of Mishchenko (2021) and Doikov and Nesterov (2021), b) we prove a local quadratic rate, which matches the best-known local rate of second-order methods, and c) our stepsize formula is simple, explicit, and does not require solving any subproblem. Our convergence proofs hold under affine-invariance assumptions closely related to …

Automs: Automatic Model Selection For Novelty Detection With Error Rate Control, Yifan Zhang, Haiyan Jiang, Haojie Ren, Changliang Zou, Dejing Dou

Machine Learning Faculty Publications

Given an unsupervised novelty detection task on a new dataset, how can we automatically select a “best” detection model while simultaneously controlling the error rate of the best model? For novelty detection analysis, numerous detectors have been proposed to detect outliers on a new unseen dataset based on a score function trained on available clean data. However, due to the absence of labeled anomalous data for model evaluation and comparison, there is a lack of systematic approaches that are able to select the “best” model/detector (i.e., the algorithm as well as its hyperparameters) and achieve certain error rate control simultaneously. …

Factored Adaptation For Non-Stationary Reinforcement Learning, Fan Feng, Biwei Huang, Kun Zhang, Sara Magliacane

Machine Learning Faculty Publications

Dealing with non-stationarity in environments (e.g., in the transition dynamics) and objectives (e.g., in the reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL). While most current approaches model the changes as a single shared embedding vector, we leverage insights from the recent causality literature to model non-stationarity in terms of individual latent change factors, and causal graphs across different environments. In particular, we propose Factored Adaptation for Non-Stationary RL (FANS-RL), a factored adaption approach that learns jointly both the causal structure in terms of a factored MDP, and a factored representation of …

Data Processing Under Fuzzy Uncertainty: Towards More Accurate Algorithms, Marina Tuyako Mizukoshi, Weldon Lodwick, Martine Ceberio, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Data that we process comes either from measurements or from experts -- or from the results of previous data processing that were also based on measurements and/or expert estimates. In both cases, the data is imprecise. To gauge the accuracy of the results of data processing, we need to take the corresponding data uncertainty into account. In this paper, we describe a new algorithm for taking fuzzy uncertainty into account, an algorithm that, for small number of inputs, leads to the same or even better accuracy than the previously proposed methods.

(R2020) Dynamical Study And Optimal Harvesting Of A Two-Species Amensalism Model Incorporating Nonlinear Harvesting, Manoj Kumar Singh, Poonam .

Applications and Applied Mathematics: An International Journal (AAM)

This study proposes a two-species amensalism model with a cover to protect the first species from the second species, with the assumption that the growth of the second species is governed by nonlinear harvesting. Analytical and numerical analyses have both been done on this suggested ecological model. Boundedness and positivity of the solutions of the model are examined. The existence of feasible equilibrium points and their local stability have been discussed. In addition, the parametric conditions under which the proposed system is globally stable have been determined. It has also been shown, using the Sotomayor theorem, that under certain parametric …

Supercontinuum Light Generation Via Non-Linear Effects In Hollow-Core Fiber, Skyler Gulati

Physics Student Works

The field of non-linear optics has gained traction in the last couple decades due to the variable generation of wavelengths which are less deterministic than within traditional optics. Using non-linear mediums, including hollow-core fibers (HCF), generation of wavelengths spanning into the vacuum ultraviolet (VUV) wavelength range is possible. These short wavelengths can be utilized within electron spectroscopy-based methods of material science like angle-resolved photoemission spectroscopy (ARPES). This technique most often uses specific photoemission lines of atoms in discharge lamps, however, with the frequency dispersion capabilities of HCF, broad band creation can allow for variable wavelength selection through filtering specific wavelengths …

A Cradle-To-Gate Life Cycle Assessment Of American Hops In The Craft Beer Supply Chain, Carson Bristol

Master of Science in Environmental Sciences and Management Projects

The hop industry represents a culturally and economically significant industry in the United States due to the product’s significant role in the beer industry, but little is known about the environmental impacts associated with hop production. There exists a significant lack of specific research quantifying the emissions contribution of hop production, and the work that has been done lacks consensus in the scientific community. In an effort to overcome this, this study conducts a cradle-to-gate life cycle assessment (LCA) of aroma hop production broken into four phases, beginning with propagation of seedlings by tissue culture and ending with packaged T-90 …

Non-Localized Physical Processes Can Help Speed Up Computations, Be It Hidden Variables In Quantum Physics Or Non-Localized Energy In General Relativity, Michael Zakharevich, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

While most physical processes are localized -- in the sense that each event can only affect events in its close vicinity -- many physicists believe that some processes are non-local. These beliefs range from more heretic -- such as hidden variables in quantum physics -- to more widely accepted, such as the non-local character of energy in General Relativity. In this paper, we attract attention to the fact that non-local processes bring in the possibility of drastically speeding up computations.

Graph Approach To Uncertainty Quantification, Hector A. Reyes, Cliff Joslyn, Vladik Kreinovich

Departmental Technical Reports (CS)

Traditional analysis of uncertainty of the result of data processing assumes that all measurement errors are independent. In reality, there may be common factor affecting these errors, so these errors may be dependent. In such cases, the independence assumption may lead to underestimation of uncertainty. In such cases, a guaranteed way to be on the safe side is to make no assumption about independence at all. In practice, however, we may have information that a few pairs of measurement errors are indeed independent -- while we still have no information about all other pairs. Alternatively, we may suspect that for …

Systems Approach Explains Why Low Heart Rate Variability Is Correlated With Depression (And Suicidal Thoughts), Francisco Zapata, Eric Smith, Vladik Kreinovich

Departmental Technical Reports (CS)

Depression is a serious medical problem. If diagnosed early, it can usually be cured, but if left undetected, it can lead to suicidal thoughts and behavior. The early stages of depression are difficult to diagnose. Recently, researchers found a promising approach to such diagnosis -- it turns out that depression is correlated with low heart rate variability. In this paper, we show that the general systems approach can explain this empirical relation.

An Argument In Favor Of Piecewise-Constant Membership Functions, Marina Tuyako Mizukoshi, Weldon Lodwick, Martine Ceberio, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Theoretically, we can have membership functions of arbitrary shape. However, in practice, at any given moment of time, we can only represent finitely many parameters in a computer. As a result, we usually restrict ourselves to finite-parametric families of membership functions. The most widely used families are piecewise linear ones, e.g., triangular and trapezoid membership functions. The problem with these families is that if we know a nonlinear relation y = f(x) between quantities, the corresponding relation between membership functions is only approximate -- since for piecewise linear membership functions for x, the resulting membership function for y is not …

Will Nanotechnology Bring In The Judgement Day?, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

There are many current and prospective positive aspects of nanotechnology. However, while we look forward to its future successes, we need to keep our eyes open and be prepared for what will really be a future shock: that quantum computing – an inevitable part of nanotechnology – will enable the future folks to read all our encrypted messages and thus, learn everything that we wanted to keep secret. This will be really the Judgement Day, when all our sins will be open to everyone. How we will react to it? Will this destroy our civilization? Let us hope that the …

Eureka: Euphemism Recognition Enhanced Through Knn-Based Methods And Augmentation, Sedrick Scott Keh, Rohit Bharadwaj, Emmy Liu, Simone Tedeschi, Varun Gangal, Roberto Navigli

Computer Vision Faculty Publications

We introduce EUREKA, an ensemble-based approach for performing automatic euphemism detection. We (1) identify and correct potentially mislabelled rows in the dataset, (2) curate an expanded corpus called EuphAug, (3) leverage model representations of Potentially Euphemistic Terms (PETs), and (4) explore using representations of semantically close sentences to aid in classification. Using our augmented dataset and kNN-based methods, EUREKA was able to achieve state-of-the-art results on the public leaderboard of the Euphemism Detection Shared Task, ranking first with a macro F1 score of 0.881.

Rare Gems: Finding Lottery Tickets At Initialization, Kartik Sreenivasan, Jy Yong Sohn, Liu Yang, Matthew Grinde, Alliot Nagle, Hongyi Wang, Eric Xing, Kangwook Lee, Dimitris Papailiopoulos

Machine Learning Faculty Publications

Large neural networks can be pruned to a small fraction of their original size, with little loss in accuracy, by following a time-consuming “train, prune, re-train” approach. Frankle & Carbin [9] conjecture that we can avoid this by training lottery tickets, i.e., special sparse subnetworks found at initialization, that can be trained to high accuracy. However, a subsequent line of work [11, 41] presents concrete evidence that current algorithms for finding trainable networks at initialization, fail simple baseline comparisons, e.g., against training random sparse subnetworks. Finding lottery tickets that train to better accuracy compared to simple baselines remains an open …

2022 Fall Engr333 Poster, Section B, Nicholas Paternoster, Nick Grossman, Jared Ruba, Zac Runhaar, Caleb Styf, Anne Ghata, Micah Lee, Thomas Noble, Liam Austin, Kai Barboza, Mark Bekhet, Jordan Tuter, Jacob Tanis, Sara Vansolkema, Aidan Bakker, Ben Casey, Sarah Maccarthy, Elise Miera, Christine Vanoyen

ENGR 333

• “What would it take to eliminate Calvin's natural gas-related net CO2 emissions?”
• Former Calvin President Michael Le Roy signed the President’s Climate Commitment on Dec 6, 2017
• Pledged carbon neutrality by 2057
• Results so far have been mixed due to the COVID-19 pandemic, but gains have come from: Improved lighting efficiency, Reduced enrollment, Renewable electricity is already being tackled through partnerships with companies like Sun FundED.

Predictions And Drivers Of Sub-Reach-Scale Annual Streamflow Permanence For The Upper Missouri River Basin: 1989–2018, Kendra E. Kaiser

Geosciences Faculty Publications and Presentations

The presence of year-round surface water in streams (i.e., streamflow permanence) is an important factor for identifying aquatic habitat availability, determining the regulatory status of streams, managing land use change, allocating water resources, and designing scientific studies. However, accurate, high resolution, and dynamic prediction of streamflow permanence that accounts for year-to-year variability at a regional extent is a major gap in modeling capability. Herein, we expand and adapt the U.S. Geological Survey (USGS) PRObability of Streamflow PERmanence (PROSPER) model from its original implementation in the Pacific Northwest (PROSPER_PNW) to the upper Missouri River basin (PROSPER_UM), a …

The Formation Of The 8˚20’ N Seamount Chain, East Pacific Rise, Dorsey Wanless

Geosciences Faculty Publications and Presentations

Near-axis seamounts provide a unique setting to investigate three-dimensional mantle processes associated with the formation of new oceanic crust and lithosphere. Here, we investigate the characteristics and evolution of the 8˚20’N Seamount Chain, a lineament of seamounts that extends ~ 175 km west of the East Pacific Rise (EPR) axis, just north of the fracture zone of the Siqueiros Transform Fault. Shipboard gravity, magnetic, and bathymetric data acquired in 2016 are utilized to constrain models of seamount emplacement and evolution. Geophysical observations indicate that these seamounts formed during four distinct episodes of volcanism coinciding with changes in regional plate motion …

What Technologies And Barriers Are Present In Sustainable Heating And Cooling, Mason D. Nibbe

Environmental Studies Student Work

Sustainable heating and cooling practices can save homeowners money and reduce their carbon emissions. In the cold upper Midwest, Minnesota specifically, there are ways houses can be more efficient in terms of heating. The most efficient and practical are heat pumps systems, passive solar designs, and proper insulation of the building. This study is targeted at both existing buildings and the construction of new buildings. This project focuses on what sustainable heating and cooling practices, technologies, and barriers are present in the heating, ventilation, and air-conditioning (HVAC) industry. I find that using any sustainable solution is helpful, but multiple solutions …

(R1969) On The Approximation Of Eventual Periodicity Of Linearized Kdv Type Equations Using Rbf-Ps Method, Hameed Ullah Jan, Marjan Uddin, Asma Norin, Tamheeda .

Applications and Applied Mathematics: An International Journal (AAM)

Water wave propagation phenomena still attract the interest of researchers from many areas and with various objectives. The dispersive equations, including a large body of classes, are widely used models for a great number of problems in the fields of physics, chemistry and biology. For instance, the Korteweg-de Vries (KdV) equation is one of the famous dispersive wave equation appeared in the theories of shallow water waves with the assumption of small wave-amplitude and large wave length, also its various modifications serve as the modeling equations in several physical problems. Another interesting qualitative characteristic of solutions of some dispersive wave …

Oak Savanna Restoration And Climate Change Mitigation Through Silvopasture In Minnesota, James Siems

Environmental Studies Student Work

Reducing emissions of world food systems will be critical to combatting climate change. Silvopasture systems, which integrate managed forests with pastureland, have been shown to be a more sustainable alternative to traditional livestock production and have the ancillary benefit of diversifying the sources of income for farmers. Silvopasture may also have the capacity to serve as a mechanism for ecological restoration. This paper combines existing literature with an interview of a farmer who is engaging in silvopasture to evaluate the potential of silvopasture as means to restore Minnesota’s disappearing oak savanna ecosystem, while improving the sustainability of food production within …

Standard Interval Computation Algorithm Is Not Inclusion-Monotonic: Examples, Marina Tuyako Mizukoshi, Weldon Lodwick, Martine Ceberio, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

When we usually process data, we, in effect, implicitly assume that we know the exact values of all the inputs. In practice, these values comes from measurements, and measurements are never absolutely accurate. In many cases, the only information about the actual (unknown) values of each input is that this value belongs to an appropriate interval. Under this interval uncertainty, we need to compute the range of all possible results of applying the data processing algorithm when the inputs are in these intervals. In general, the problem of exactly computing this range is NP-hard, which means that in feasible time, …

Aquaculture In Africa: Aquatic Animal Welfare, Impact On The Environment And The Sustainability Of The Sector, Mwenda M. Mbaka, Janice H. Cox, Stephen Ronan

Aquaculture

The African aquaculture sector recorded the fastest growth in the world between 2006-2018, averaging 10% or more, and is expected to partially fill the growing fish supply-demand gap up to 2063. In 2018, there were about 1.2 million aquafarmers across the continent, an increase from 920 thousand in 2014. According to the African Development Bank, expansion of aquaculture in Africa is hampered by "the overwhelming predominance of tilapia farming, which relies heavily on the production of fingerlings from a limited number of genetically improved strains that are resistant to the many diseases affecting this species, and on the production of …

Assessing The Effectiveness Of Climate Change Science Communication In An Online Carbon Footprint Assessment, Jack Dimmock

Master of Science in Environmental Sciences and Management Projects

Climate change literacy and knowledge are influential in enabling people to take climate change mitigation and adaptation actions. Education about climate change usually takes place through two avenues, formal education and informal institutions, such as museums, television shows, and websites. To help residents reduce their household greenhouse gas emissions and adapt to the local impacts of climate change, the San Luis Obispo Climate Coalition is using the carbon footprint website Bright Action (https://resilientslo.org). Bright Action calculates household carbon footprints, suggests ways to reduce carbon footprints, and provides educational material about climate change mitigation and adaptation. This study seeks to assess …

Independence Testing-Based Approach To Causal Discovery Under Measurement Error And Linear Non-Gaussian Models, Haoyue Dai, Peter Spirtes, Kun Zhang

Machine Learning Faculty Publications

Causal discovery aims to recover causal structures generating the observational data. Despite its success in certain problems, in many real-world scenarios the observed variables are not the target variables of interest, but the imperfect measures of the target variables. Causal discovery under measurement error aims to recover the causal graph among unobserved target variables from observations made with measurement error. We consider a specific formulation of the problem, where the unobserved target variables follow a linear non-Gaussian acyclic model, and the measurement process follows the random measurement error model. Existing methods on this formulation rely on non-scalable over-complete independent component …

(R1958) On Deferred Statistical Convergence Of Fuzzy Variables, Ömer Kişi, Mehmet Gürdal, Ekrem Savaş

Applications and Applied Mathematics: An International Journal (AAM)

In this paper, within framework credibility theory, we examine several notions of convergence and statistical convergence of fuzzy variable sequences. The convergence of fuzzy variable sequences such as the notion of convergence in credibility, convergence in distribution, convergence in mean, and convergence uniformly virtually certainly via postponed Cesàro mean and a regular matrix are researched using fuzzy variables. We investigate the connections between these concepts. Significant results on deferred statistical convergence for fuzzy variable sequences are thoroughly investigated.

Phase Transitions In Evolutionary Dynamics, Adam D. Scott, Dawn M. King, Stephen W. Ordway, Sonya Bahar

Physics Faculty Works

Sharp changes in state, such as transitions from survival to extinction, are hallmarks of evolutionary dynamics in biological systems. These transitions can be explored using the techniques of statistical physics and the physics of nonlinear and complex systems. For example, a survival-to-extinction transition can be characterized as a non-equilibrium phase transition to an absorbing state. Here, we review the literature on phase transitions in evolutionary dynamics. We discuss directed percolation transitions in cellular automata and evolutionary models, and models that diverge from the directed percolation universality class. We explore in detail an example of an absorbing phase transition in an …

A Comparison Of Logistic, Ridge, And Lasso Regression With Heart Failure Risk Data: Effects Of Sample Size, Predictor Correlation, And Predictor Weight On Outcome Accuracy, Mahmoud M. Aljuhani

Electronic Theses and Dissertations

Logistic Regression (LR), LASSO regression, and RIDGE regression are standard classification techniques for predicting a dichotomous output. Since these methods are applied for similar purposes and have different features, it is crucial to evaluate the performance of these methods under different controlled conditions. With this information, researchers can apply the optimal method for specific conditions.

Following previous research, which reported the effects of conditions such as sample size and multicollinearity on the performance of the classification methods, this research focused on the effects of when sample size, level of predictor collinearity, and predictor variable weight are controlled on the performance …