Scalable Gradients for Stochastic Differential Equations

The adjoint sensitivity method scalably computes gradients of solutions toordinary differential equations. We generalize this method to stochasticdifferential equations, allowing time-efficient... | Continue reading | 1 day ago

A New Direction in Firefighting Systems

Recent huge technological development of Unmanned Aerial Vehicles (UAVs) canprovide breakthrough means of fighting wildland fires. We propose an innovativeforest firefighting system based on the... | Continue reading | 1 day ago

Domain-Specific Multi-Level IR Rewriting for GPU

Traditional compilers operate on a single generic intermediate representation(IR). These IRs are usually low-level and close to machine instructions. As aresult, optimizations relying on... | Continue reading | 1 day ago

Global Decision-Making via Local Economic Transactions

This paper seeks to establish a framework for directing a society of simple,specialized, self-interested agents to solve what traditionally are posed asmonolithic single-agent sequential... | Continue reading | 2 days ago

Logarithmic Pruning Is All You Need

The Lottery Ticket Hypothesis is a conjecture that every large neural networkcontains a subnetwork that, when trained in isolation, achieves comparableperformance to the large network. An even... | Continue reading | 3 days ago

Neutral monism, perspectivism and the quantum dualism: An essay

Quantum mechanics in the Wigner-von Neumann interpretation is presented. Thisis characterized by 1) a quantum dualism between matter and consciousnessunified within an informational neutral... | Continue reading | 3 days ago

Neural programmer better than Quicksort

We study the problem of learning efficient algorithms that stronglygeneralize in the framework of neural program induction. By carefully designingthe input / output interfaces of the neural... | Continue reading | 3 days ago

Politeness Transfer: A Tag and Generate Approach

This paper introduces a new task of politeness transfer which involvesconverting non-polite sentences to polite sentences while preserving themeaning. We also provide a dataset of more than 1.39... | Continue reading | 5 days ago

You Only Look Once: Unified, Real-Time Object Detection

We present YOLO, a new approach to object detection. Prior work on objectdetection repurposes classifiers to perform detection. Instead, we frame objectdetection as a regression problem to... | Continue reading | 5 days ago

YOLO9000: Better, Faster, Stronger

We introduce YOLO9000, a state-of-the-art, real-time object detection systemthat can detect over 9000 object categories. First we propose variousimprovements to the YOLO detection method, both... | Continue reading | 5 days ago

Differences of OT/CRDT: General Transformation Frameworks, Co-Editor Consistency

OT (Operational Transformation) was invented for supporting real-timeco-editors in the late 1980s and has evolved to become a core technique used intoday's working co-editors and adopted in... | Continue reading | 6 days ago

DomainBed: In Search of Lost Domain Generalization

The goal of domain generalization algorithms is to predict well ondistributions different from those seen during training. While a myriad ofdomain generalization algorithms exist,... | Continue reading | 7 days ago

One of Everything: The Breakthrough Listen Exotica Catalog

We present Breakthrough Listen's "Exotica" Catalog as the centerpiece of ourefforts to expand the diversity of targets surveyed in the Search forExtraterrestrial Intelligence (SETI). As... | Continue reading | 8 days ago

Projectile Trajectory of Penguin's Faeces and Rectal Pressure Revisited

We discuss a trajectory of penguins' faeces after the powerful shooting dueto their strong rectal pressure. Practically, it is important to see how farfaeceses reach when penguins expel them... | Continue reading | 8 days ago

Dependent Types in Haskell: Theory and Practice (2016)[pdf]

Haskell, as implemented in the Glasgow Haskell Compiler (GHC), has beenadding new type-level programming features for some time. Many of thesefeatures---chiefly: generalized algebraic datatypes... | Continue reading | 8 days ago

Training Convolutional ReLU Neural Networks in Polynomial Time

We study training of Convolutional Neural Networks (CNNs) with ReLUactivations and introduce exact convex optimization formulations with apolynomial complexity with respect to the number of data... | Continue reading | 9 days ago

Early Warning Approach to Monitor Covid-19 with Digital Traces in Near Real-Time

Non-pharmaceutical interventions (NPIs) have been crucial in curbing COVID-19in the United States (US). Consequently, relaxing NPIs through a phasedre-opening of the US amid still-high levels of... | Continue reading | 9 days ago

Approaching Optimal Duplicate Detection in a Sliding Window [pdf]

Duplicate detection is the problem of identifying whether a given item haspreviously appeared in a (possibly infinite) stream of data, when only alimited amount of memory is available. ... | Continue reading | 9 days ago

Paradox with just self-reference [pdf]

If a semantically open language has no constraints on self-reference, one canshow there is a predicate which is both satisfied and unsatisfied by aself-referring term. The argument requires... | Continue reading | 9 days ago

ReversiSpec: Reversible Coherence Protocol for Defending Transient Attacks

The recent works such as InvisiSpec, SafeSpec, and Cleanup-Spec, amongothers, provided promising solutions to defend speculation induced (transient)attacks. However, they intro-duce delay either... | Continue reading | 10 days ago

Queues are Databases (1995)

Message-oriented-middleware (MOM) has become an small industry. MOM offersqueued transaction processing as an advance over pure client-server transactionprocessing. This note makes four points:... | Continue reading | 10 days ago

What is the state of neural network pruning?

Neural network pruning---the task of reducing the size of a network byremoving parameters---has been the subject of a great deal of work in recentyears. We provide a meta-analysis of the... | Continue reading | 10 days ago

Differentiate Everything with a Reversible Domain-Specific Language

Traditional machine instruction level reverse mode automatic differentiation(AD) faces the problem of having a space overhead that linear to time in orderto trace back the computational state,... | Continue reading | 11 days ago

Synthetic Data for Deep Learning

Synthetic data is an increasingly popular tool for training deep learningmodels, especially in computer vision but also in other areas. In this work, weattempt to provide a comprehensive survey... | Continue reading | 11 days ago

600B parameter Transformer trained by Google

Neural network scaling has been critical for improving the model quality inmany real-world machine learning applications with vast amounts of trainingdata and compute. Although this trend of... | Continue reading | 11 days ago

The nature of programming exercises [pdf]

There are countless reasons cited in scientific studies to explain thedifficulties in programming learning. The reasons range from the subject'scomplexity, the ineffective teaching and study... | Continue reading | 12 days ago

Show HN: Control of Sliding-Arm-Quadcopter with DynamicStructuralParameters

The conceptual design and flight controller of a novel kind of quadcopter arepresented. This design is capable of morphing the shape of the UAV duringflight to achieve position and attitude... | Continue reading | 12 days ago

DJB: Is the security of quantum cryptography guaranteed by the laws of physics?

It is often claimed that the security of quantum key distribution (QKD) isguaranteed by the laws of physics. However, this claim is content-free if theunderlying theoretical definition of QKD is... | Continue reading | 13 days ago

Articles downloaded from SciHub where cited 1.72 times more

Citations are often used as a metric of the impact of scientificpublications. Here, we examine how the number of downloads from Sci-hub as wellas various characteristics of publications and... | Continue reading | 13 days ago

Discovering Symbolic Models from Deep Learning with Inductive Biases

We develop a general approach to distill symbolic representations of alearned deep model by introducing strong inductive biases. We focus on GraphNeural Networks (GNNs). The technique works as... | Continue reading | 15 days ago

Using machine learning to classify story arcs into six basic shapes

Advances in computing power, natural language processing, and digitization oftext now make it possible to study a culture's evolution through its textsusing a "big data" lens. Our ability to... | Continue reading | 15 days ago

Pull out all the stops: Textual analysis via punctuation sequences

Whether enjoying the lucid prose of a favorite author or slogging throughsome other writer's cumbersome, heavy-set prattle (full of parentheses, emdashes, compound adjectives, and Oxford... | Continue reading | 15 days ago

Atmospheric Regimes and Trends on Exoplanets and Brown Dwarfs

A planetary atmosphere is the outer gas layer of a planet. Besides itsscientific significance among the first and most accessible planetary layersobserved from space, it is closely connected... | Continue reading | 16 days ago

On the role of the Michelson-Morley experiment: Einstein in Chicago [pdf]

Continue reading | 17 days ago

Simplify-Then-Translate:Automatic Preprocessing for BlackBox Machine Translation

Black-box machine translation systems have proven incredibly useful for avariety of applications yet by design are hard to adapt, tune to a specificdomain, or build on top of. In this work, we... | Continue reading | 17 days ago

The NetHack Learning Environment

Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand with thedevelopment of challenging environments that test the limits of currentmethods. While existing RL environments are... | Continue reading | 18 days ago

LiteX: An open-source SoC builder and library based on Migen Python DSL

LiteX is a GitHub-hosted SoC builder / IP library and utilities that can beused to create SoCs and full FPGA designs. Besides being open-source and BSDlicensed, its originality lies in the fact... | Continue reading | 18 days ago

Collective Learning by Ensembles of Altruistic Diversifying Neural Networks

Combining the predictions of collections of neural networks often outperformsthe best single network. Such ensembles are typically trained independently,and their superior `wisdom of the crowd'... | Continue reading | 18 days ago

Learning to Classify Images Without Labels

Is it possible to automatically classify images without the use ofground-truth annotations? Or when even the classes themselves, are not a prioriknown? These remain important, and open questions... | Continue reading | 19 days ago

Deep Learning Based Text Classification: A Comprehensive Review

Deep learning based models have surpassed classical machine learning basedapproaches in various text classification tasks, including sentiment analysis,news categorization, question answering,... | Continue reading | 19 days ago

DreamCoder: Growing generalizable, interpretable knowledge with program learning

Expert problem-solving is driven by powerful languages for thinking aboutproblems and their solutions. Acquiring expertise means learning theselanguages -- systems of concepts, alongside the... | Continue reading | 20 days ago

Inferring population properties of binary black holes from gravitational waves

The vast majority of compact binary mergers in the Universe producegravitational waves that are too weak to yield unambiguous detections; they areunresolved. We present a method to infer the... | Continue reading | 21 days ago

The never ending war in the stack and the reincarnation of ROP attacks

Return Oriented Programming (ROP) is a technique by which an attacker caninduce arbitrary behavior inside a vulnerable program without injecting amalicious code. The continues failure of the... | Continue reading | 22 days ago

A Tutorial on VAEs: From Bayes' Rule to Lossless Compression

The Variational Auto-Encoder (VAE) is a simple, efficient, and popular deepmaximum likelihood model. Though usage of VAEs is widespread, the derivation ofthe VAE is not as widely understood. In... | Continue reading | 22 days ago

Practical Black-Box Attacks Against Machine Learning

Machine learning (ML) models, e.g., deep neural networks (DNNs), arevulnerable to adversarial examples: malicious inputs modified to yielderroneous model outputs, while appearing unmodified to... | Continue reading | 22 days ago

Big Self-Supervised Models Are Strong Semi-Supervised Learners

One paradigm for learning from few labeled examples while making best use ofa large amount of unlabeled data is unsupervised pretraining followed bysupervised fine-tuning. Although this paradigm... | Continue reading | 23 days ago

Using AI to Improve Maternal Health Outcomes by Increasing Intervention [pdf]

India accounts for 11% of maternal deaths globally where a woman dies inchildbirth every fifteen minutes. Lack of access to preventive care informationis a significant problem contributing to... | Continue reading | 24 days ago

A Woman Worked as a Babysitter: On Biases in Language Generation

We present a systematic study of biases in natural language generation (NLG)by analyzing text generated from prompts that contain mentions of differentdemographic groups. In this work, we... | Continue reading | 24 days ago