arXiv research

Inception v3 model classifies face shapes with high accuracy.

Satellite imagery improves house price prediction models.

Paper proposes evaluation methods for climate change illustrations.

Adversarial examples are of wide concern due to their impact on the reliability of contemporary machine learning systems. Effective adversarial examples are mostly found via white-box attacks. However, in some cases they can be transferred across models, thus enabling them to attack black-box models. In this work we ev…

Uniswap v3 LPs suffer significant Impermanent Loss despite higher fees.

A cost-effective method to generate high-resolution images using wavelet-based super-resolution.

While deep neural networks have proven to be a powerful tool for many recognition and classification tasks, their stability properties are still not well understood. In the past, image classifiers have been shown to be vulnerable to so-called adversarial attacks, which are created by additively perturbing the correctly…

Neural network models have a reputation for being black boxes. We propose to monitor the features at every layer of a model and measure how suitable they are for classification. We use linear classifiers, which we refer to as "probes", trained entirely independently of the model itself. This helps us better understand …

Deep Convolutional Networks (DCNs) have been shown to be vulnerable to adversarial examples---perturbed inputs specifically designed to produce intentional errors in the learning algorithms at test time. Existing input-agnostic adversarial perturbations exhibit interesting visual patterns that are currently unexplained…

In many machine learning applications, it is important to explain the predictions of a black-box classifier. For example, why does a deep neural network assign an image to a particular class? We cast interpretability of black-box classifiers as a combinatorial maximization problem and propose an efficient streaming alg…

Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we present a large batch, stochastic optimization algorithm that is both faster tha…

Capsule Networks (CN) offer new architectures for Deep Learning (DL) community. Though its effectiveness has been demonstrated in MNIST and smallNORB datasets, the networks still face challenges in other datasets for images with distinct contexts. In this research, we improve the design of CN (Vector version) namely we…

Uniswap V3 requires more decisions from liquidity providers, making it complex and risky.

Study how neural networks optimize to stable linearly connected regions.

Uniswap V3 struggles with price accuracy during sudden market drops.

Motivated by applications in computational advertising and systems biology, we consider the problem of identifying the best out of several possible soft interventions at a source node $V$ in an acyclic causal directed graph, to maximize the expected value of a target node $Y$ (located downstream of $V$). Our setting im…

In this paper, the effectiveness and capability of convolutional neural networks have been studied in the classification of 8 skin diseases. Different pre-trained state-of-the-art architectures (DenseNet 201, ResNet 152, Inception v3, InceptionResNet v2) were used and applied on 10135 dermoscopy skin images in total (H…

Paper introduces a new pricing model for Uniswap V3 positions.

Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerous misclassifications. We propose a novel way to interpret adversarial perturbations in terms of the effective input signal that classifiers …

Neuron Shapley identifies key neurons in deep networks, improving model accuracy and fairness.

The robustness of neural networks to adversarial examples has received great attention due to security implications. Despite various attack approaches to crafting visually imperceptible adversarial examples, little has been developed towards a comprehensive measure of robustness. In this paper, we provide a theoretical…

Study identifies and mitigates causes of image misclassifications in CNN models.

Replicates and improves Uniswap V3 model using DDQN and Mamba.

Learning to learn has emerged as an important direction for achieving artificial intelligence. Two of the primary barriers to its adoption are an inability to scale to larger problems and a limited ability to generalize to new tasks. We introduce a learned gradient descent optimizer that generalizes well to new tasks, …

The problem of video frame prediction has received much interest due to its relevance to many computer vision applications such as autonomous vehicles or robotics. Supervised methods for video frame prediction rely on labeled data, which may not always be available. In this paper, we provide a novel unsupervised deep-l…

The paper examines how cheaper and faster chains affect Uniswap v3 liquidity and profitability.

Study optimal liquidation strategies on Uniswap v2/v3 considering price impact.

Graph partitioning is the problem of dividing the nodes of a graph into balanced partitions while minimizing the edge cut across the partitions. Due to its combinatorial nature, many approximate solutions have been developed, including variants of multi-level methods and spectral clustering. We propose GAP, a Generaliz…

Runtime and scalability of large neural networks can be significantly affected by the placement of operations in their dataflow graphs on suitable devices. With increasingly complex neural network architectures and heterogeneous device characteristics, finding a reasonable placement is extremely challenging even for do…

Compound Finance optimizes risk metrics for V3 protocol using Chainrisk simulations.

This paper formalizes Uniswap v3 using PTA and FST for rigorous analysis.

Deep learning models can take weeks to train on a single GPU-equipped machine, necessitating scaling out DL training to a GPU-cluster. However, current distributed DL implementations can scale poorly due to substantial parameter synchronization over the network, because the high throughput of GPUs allows more data batc…

Study on liquidity dynamics in Uniswap v3 pools using statistical methods.

Backtesting framework for CLMMs on Uniswap V3 reduces reward estimation error.

Robotic weed control has seen increased research of late with its potential for boosting productivity in agriculture. Majority of works focus on developing robotics for croplands, ignoring the weed management problems facing rangeland stock farmers. Perhaps the greatest obstacle to widespread uptake of robotic weed con…

Deploying deep learning (DL) models across multiple compute devices to train large and complex models continues to grow in importance because of the demand for faster and more frequent training. Data parallelism (DP) is the most widely used parallelization strategy, but as the number of devices in data parallel trainin…

New algorithm B++&C improves hierarchical clustering on large deep embedding datasets.

Panoptic trades options without oracles on Ethereum.

RS-NN predicts belief functions for classification, improving accuracy and uncertainty estimation.

Developing an Agent-Based Model to Mitigate Adverse Selection in Uniswap v3 Liquidity Providers

Study analyzes risk management in Aave and Compound lending protocols, finding v3 better than v2.

In this article, we mathematically study several GAN related topics, including Inception score, label smoothing, gradient vanishing and the -log(D(x)) alternative. --- An advanced version is included in arXiv:1703.02000 "Activation Maximization Generative Adversarial Nets". Please refer Section 6 in 1703.02000 for deta…

Study examines stylized facts in DEX markets vs. traditional exchanges.

Hyperbolic GANs improve image generation metrics.

Improves GANs by incorporating class information with a multi-hinge loss.

Proposes Topology Distance for evaluating GANs.

Study characterizes Uniswap v3 liquidity pools using transaction graphs and identifies ideal trading conditions.

In this short note, we propose an unified method to derive formulas for derivations conjugated by exponential functions on an almost complex manifold. In v3, we corrected some mistakes in previous versions.