Bitcoin fails to function as a stable currency or store of value.
problem Bitcoin's failure to serve as a reliable currency or store of value.
method Quantitative finance methods and economic arguments applied to cryptocurrencies.
result Bitcoin does not function as a currency, store of value, or inflation hedge.
This study compares Bitcoin and Litecoin using cryptocurrency metrics and trading strategies.
problem Valuation and trading strategies for cryptocurrencies.
method Metrics like UTXO, STXO, WAL, CDD, and trading strategies based on PU ratio.
result Bitcoin's superior store-of-value proposition compared to Litecoin validated.
In this paper, we reveal the attenuation mechanism of anchor of the commodity money from the perspective of logistics warehousing costs, and propose a novel Decayed Commodity Money (DCM) for the store of value across time and space. Considering the logistics cost of commodity warehousing by the third financial institut…
Efficiently stores and retrieves past states for faster learning in reinforcement learning.
problem Data inefficiency and memory limitations in reinforcement learning.
method Dynamic online k-means for state clustering and prioritization.
result Dynamic online k-means improves performance with smaller memory sizes.
The paper reveals the hidden costs of digitizing commodity money and proposes a new stable-coin system.
problem Depreciation of banknotes due to high logistics costs after digitization.
method Analyzing the functions of money from a logistics perspective and comparing commodity money to digital currency.
result There is no honest money that is both a store of value and has negligible logistics costs.
Linear memory stores associations up to a logarithmic scale, but listwise retrieval can handle a quadratic scale.
problem How many key-value associations can a linear memory store?
method Analyzed linear memory models for top-1 and listwise retrieval, proving phase transitions and developing asymptotic theories.
result Linear memory has a logarithmic capacity for top-1 retrieval and a quadratic capacity for listwise retrieval.
Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience. Our main finding is that standard overparameterized deep neural networks trained using standard optimization methods implement such a mechanism for real-valued…
Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern…
Transformers can store facts efficiently using associative memories.
problem Understanding how transformers store and recall factual information.
method Proved linear scaling of storage capacities for linear and MLP associative memories, introduced a synthetic task, and analyzed gradient flow.
result Shallow transformers can achieve near optimal storage capacity for factual recall tasks using associative memories.
COIN++ compresses multiple data types efficiently.
problem Handling diverse data modalities in neural compression.
method Implicit neural representations and modulations quantization.
result Significant compression gains with reduced encoding time.
Grid-scale batteries' bid patterns in price uncertainty markets
problem Interpreting bids from grid-scale batteries in wholesale electricity markets under price uncertainty
method Developing an asset-level model of a price-taking battery
result Empirical results deliver insights into withholding behavior, uncertainty effects, and risk management reshaping bid curves
In this study, the authors develop a structural model that combines a macro diffusion model with a micro choice model to control for the effect of social influence on the mobile app choices of customers over app stores. Social influence refers to the density of adopters within the proximity of other customers. Using a …
Estimating the value function for a fixed policy is a fundamental problem in reinforcement learning. Policy evaluation algorithms---to estimate value functions---continue to be developed, to improve convergence rates, improve stability and handle variability, particularly for off-policy learning. To understand the prop…
Paper applies RL to optimize inventory management across multiple products and nodes.
problem Optimizing inventory management for a large number of products with shared capacity in a multi-node supply chain.
method Novel multi-agent hierarchical reinforcement learning framework with A2C algorithm and quantised action spaces.
result The approach optimizes for maximizing product sales and minimizing wastage of perishable products.
Typical large-scale recommender systems use deep learning models that are stored on a large amount of DRAM. These models often rely on embeddings, which consume most of the required memory. We present Bandana, a storage system that reduces the DRAM footprint of embeddings, by using Non-volatile Memory (NVM) as the prim…
FEM improves attention mechanisms by applying value-driven log-linear tilts.
problem Standard attention mechanisms read via convex average, limiting channel-wise selection.
method Free Energy Mixer (FEM) applies a value-driven, per-channel log-linear tilt to a fast prior over indices.
result FEM outperforms strong baselines on NLP, vision, and time-series tasks.
Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production, especially when models need to be frequently re-trained on updated datasets. In…
We investigate relationship between annual electric power consumption per capita and gross domestic production (GDP) per capita for 131 countries. We found that the relationship can be fitted with a power-law function. We examine the relationship for 47 prefectures in Japan. Furthermore, we investigate values of annual…
A new memory system handles non-stationary environments by self-sizing and retaining memories.
problem Non-stationary environments where memories arrive over time and must be distinguished from noise.
method A self-sizing continual associative memory that generalizes Hopfield's network, handling adaptation and novelty.
result The memory system grows to the intrinsic memory demand of the environment and retains memories without forgetting.
The brain optimizes memory by forgetting what's predictable, improving generalization.
problem Memory consolidation struggles with representational drift, semanticisation, and offline replay.
method Proposes predictive forgetting as a mechanism to optimize generalization by reducing complexity.
result Predictive forgetting improves information-theoretic generalization bounds on stored representations.
Model combines long-term and short-term memory using conceptors.
problem Transfer between long-term and short-term memory.
method Recurrent neural network with gated reservoir for short-term memory and conceptors for long-term memory.
result Standard operations on conceptors allow combining long-term memories and describing their effect on short-term memory.
New method improves sales forecasting accuracy using tensor factorization.
problem Improving sales forecasting accuracy in retail businesses.
method Advanced Temporal Latent-factor Approach to Sales forecasting (ATLAS) using tensor factorization.
result Accurate and individualized prediction for sales across multiple stores and products.
Two potential bottlenecks on the expressiveness of recurrent neural networks (RNNs) are their ability to store information about the task in their parameters, and to store information about the input history in their units. We show experimentally that all common RNN architectures achieve nearly the same per-task and pe…
This paper presents a novel method for information interpretability in an MC-SEFRON classifier. To develop a method to extract knowledge stored in a trained classifier, first, the binary-class SEFRON classifier developed earlier is extended to handle multi-class problems. MC-SEFRON uses the population encoding scheme t…
Sharp limits found for storing and retrieving input-output associations in linear associative memories.
problem Understanding the fundamental limits of storing and retrieving input-output associations in neural networks.
method Study of a minimal linear associative memory model, introducing a decoupled model and using statistical physics to characterize storage capacity.
result Linear associative memory can store up to 1/2 log(p) associations, providing a sharp statistical-physics characterization.
GMED edits stored examples to improve continual learning.
problem Catastrophic forgetting in task-free continual learning.
method Gradient-based memory editing of stored examples.
result GMED-edited examples help prevent forgetting.
Automates UI implementation from designer images.
problem Automating UI implementation from designer images.
method Generative model training and imitation learning.
result 92.5% accuracy on Android Button attribute inference.
Tensor network decomposition, originated from quantum physics to model entangled many-particle quantum systems, turns out to be a promising mathematical technique to efficiently represent and process big data in parsimonious manner. In this study, we show that tensor networks can systematically partition structured dat…
Bayesian method reconstructs neural network memories from connectivity.
problem Reconstructing memories from neural network connectivity.
method Bayesian inference using statistical physics principles.
result Algorithm successfully reconstructs stored patterns from synaptic connectivity.
The paper simulates Lévy processes and their extremum and hitting time.
problem Simulating Lévy processes and their extremum and hitting time accurately and efficiently.
method Using characteristic functions and conditional characteristic functions, with conformal deformations and precalculated values on multi-grids.
result Accurate and fast simulation of Lévy processes and their extremum and hitting time.
Motivated by applications in neuroimaging analysis, we propose a new regression model, Sparse TensOr REsponse regression (STORE), with a tensor response and a vector predictor. STORE embeds two key sparse structures: element-wise sparsity and low-rankness. It can handle both a non-symmetric and a symmetric tensor respo…
Improved perturbation reduces matrix condition number to O(n) with minimal storage.
problem Reducing the condition number of deterministic matrices for efficient algorithmic use.
method Introduced pattern matrices and sparse perturbations with dependent entries.
result Condition number reduced to O(n) with O(n) random numbers in O(log n) precision.
IAM improves deep RL by selectively storing influential past observations.
problem Training and performance issues with recurrent neural networks in high-dimensional environments.
method Influence-aware memory architecture that restricts input to variables influencing hidden state.
result IAM outperforms standard RNNs in training speed and policy performance.
A novel approach stores encoded images as centroids and covariance matrices to improve classification accuracy with less memory.
problem Catastrophic forgetting and memory limitations in continual learning.
method Trains autoencoders with Neural Style Transfer to encode images, replay encoded episodes to avoid forgetting, and use centroids and covariance matrices for pseudo-images when memory is full.
result Increases classification accuracy by 13-17% over state-of-the-art methods on benchmark datasets, while requiring 78% less storage space.
Develops a Bayesian model to predict business revenue and demand.
problem Estimating revenue and demand at business facilities.
method Variational Bayesian spatial interaction model (BSIM) with scalable inference.
result BSIM outperforms competing approaches in predicting pub revenue and demand.
FF layers in transformers are nearly as interpretable as sparse autoencoders.
problem Comparing interpretability of feature vectors in FF layers vs. sparse autoencoders.
method Revisited interpretability of FF layers as key-value memories using modern benchmarks.
result FF and SAE feature vectors are similarly interpretable, but FFs can be better in some aspects.
New method reduces word embedding storage space by 100x.
problem Large space required for storing word embeddings.
method Inspired by quantum computing, proposes word2ket and word2ketXS methods.
result Achieves a hundred-fold reduction in space required for word embeddings.
Estimates Markov chain variance efficiently without storing samples.
problem Estimating the asymptotic variance of Markov chain functions.
method Linear stochastic approximation of Poisson equation solution.
result Optimal MSE convergence rate with finite sample guarantees.
Experience reuse is key to sample-efficient reinforcement learning. One of the critical issues is how the experience is represented and stored. Previously, the experience can be stored in the forms of features, individual models, and the average model, each lying at a different granularity. However, new tasks may requi…
Enhances sequence memory capacity in neural networks.
problem Limited sequence capacity in Hopfield-like neural networks.
method Introducing a nonlinear interaction term and a generalized pseudoinverse rule.
result Significantly increased sequence capacity with novel scaling laws.
Paper proposes a uniqueness Shapley measure to compare variable importance.
problem Comparing the importance of different variables in identifying subjects.
method Uses Shapley value to combine reductions in log cardinality due to revealing variables.
result Demonstrates speedup in calculating variable importance.
We present a new method of estimating the distribution of sales rates of, e.g., book titles at an online bookstore, from the time evolution of ranking data found at websites of the store. The method is based on new mathematical results on an infinite particle limit of the stochastic ranking process, and is suitable for…
Random matrix analysis reveals that neural network weights are mostly random, with some indicating learned information.
problem Understanding how neural networks store information needed for tasks.
method Random matrix theory (RMT) applied to weight matrices of trained deep neural networks.
result Most singular values and eigenvectors of trained neural networks follow universal RMT predictions, suggesting they are random and do not contain system-specific information.
A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.
problem Stabilizing model-free off-policy deep reinforcement learning with soft divergence.
method Representing past experiences as a QGraph, selecting a subgraph with favorable structure, and using lower bounds for temporal difference learning.
result QG-DDPG method is less prone to soft divergence and more robust to hyperparameters.
Estimates shared parameters across related learning problems using robust statistics and LASSO.
problem Simultaneously learning related but heterogeneous problems like store demand or patient risk.
method Two-stage multitask learning estimator combining robust statistics and LASSO regression.
result Improved sample complexity bounds for multitask learning, especially beneficial for 'data-poor' instances.
OpenGM is a C++ template library for defining discrete graphical models and performing inference on these models, using a wide range of state-of-the-art algorithms. No restrictions are imposed on the factor graph to allow for higher-order factors and arbitrary neighborhood structures. Large models with repetitive struc…
Although RNNs have been shown to be powerful tools for processing sequential data, finding architectures or optimization strategies that allow them to model very long term dependencies is still an active area of research. In this work, we carefully analyze two synthetic datasets originally outlined in (Hochreiter and S…
In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform …