A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Efficiently combines autoregressive and set-based models for joint distributions.
New method allows real-time audio synthesis using non-causal convolutions.
Paper relaxes faithfulness assumption for causal discovery using interventions.
Secure aggregation for buffered asynchronous federated learning without TEEs.
We introduce a Markovian single point process model, with random intensity regulated through a buffer mechanism and a self-exciting effect controlling the arrival stream to the buffer. The model applies the principle of the Hawkes process in which point process jumps generate a shot-noise intensity field. Unlike the Ha…
A new buffer system improves continual learning in RL agents by adapting to changing environments.
This study examines how risky investments affect insurance capital valuation.
Regulator allocates buffers to prevent financial contagion in networks with common assets.
We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate. MAPO is applicable to deterministic environments with discrete actions, such as structured prediction and combinatorial optimization ta…
The paper proposes a method to learn from both simulation and real-world data.
Hierarchical GANs reduce anomaly detection costs.
We propose a novel defense against all existing gradient based adversarial attacks on deep neural networks for image classification problems. Our defense is based on a combination of deep neural networks and simple image transformations. While straightforward in implementation, this defense yields a unique security pro…
MER algorithm speeds up VI solving with Markovian data.
State space models (SSMs) provide a flexible framework for modeling complex time series via a latent stochastic process. Inference for nonlinear, non-Gaussian SSMs is often tackled with particle methods that do not scale well to long time series. The challenge is two-fold: not only do computations scale linearly with t…
A mean-reverting financial instrument is optimally traded by buying it when it is sufficiently below the estimated `mean level' and selling it when it is above. In the presence of linear transaction costs, a large amount of value is paid away crossing bid-offers unless one devises a `buffer' through which the price mus…
Investigates multi-period portfolio optimization for DC plans using buffered Probability of Exceedance.
A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural networks. To prevent forgetting, a replay buffer is usually employed to store the p…
DAC enhances exploration in reinforcement learning with entropy regularization.
Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade on old tasks when trained successively on new tasks with different data distrib…
SOCP uses SOM to find groups and local calibration buffers for better regional coverage.
Investigates optimal pension policies in PAYG systems with forward utility and ageing population.
Proportional transaction costs present difficult theoretical problems in trading algorithm design, on account of their lack of analytical tractability. The author derives a solution of DT-NT-DT form for an arbitrary model in which the the traded asset has diffusive dynamics described by one or more stochastic risk fact…
Novel asynchronous SGD method resists Byzantine attacks without server storage.
Tiled Squeeze-and-Excite improves channel attention with local spatial context.
Improved diffusion models for sampling from given distributions.
The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this technique has also been demonstrated to select suboptimal variational parameters, often resulting in consi…
Poor economies not only produce less; they typically produce things that involve fewer inputs and fewer intermediate steps. Yet the supply chains of poor countries face more frequent disruptions---delivery failures, faulty parts, delays, power outages, theft, government failures---that systematically thwart the product…
LiDER refreshes past experiences in RL by dreaming about them.
Paper develops a model-based RL framework for portfolio optimization in financial markets.
Proposes a new policy gradient algorithm to improve reinforcement learning efficiency and stability.
In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biase…
This paper considers a transmission control problem in network-coded two-way relay channels (NC-TWRC), where the relay buffers random symbol arrivals from two users, and the channels are assumed to be fading. The problem is modeled by a discounted infinite horizon Markov decision process (MDP). The objective is to find…
The paper optimizes pension policies with guarantees and sustainability constraints.
PipeDream-2BW accelerates large model training by 20x with minimal memory usage.
ETGL-DDPG improves DDPG for sparse reward control with new exploration and replay techniques.
We propose a streaming submodular maximization algorithm "stream clipper" that performs as well as the offline greedy algorithm on document/video summarization in practice. It adds elements from a stream either to a solution set or to an extra buffer based on two adaptive thresholds, and improves by a final…
It had been believed in the conventional practice that the risk of a bank going bankrupt is lessened in a straightforward manner by transferring the risk of loan defaults. But the failure of American International Group in 2008 posed a more complex aspect of financial contagion. This study presents an extension of the …
New method improves ABI for sequential data, reducing forgetting and improving accuracy.
Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy methods bring many benefits, such as ability to evaluate each resulting policy. However, they usually d…
A distributed system identification method for LTI systems using reverse experience replay.
Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow. Recent work demonstrated that using a memory buffer of previous successful trajectories can result in more effective…
A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In prior works, transitions are uniformly sampled at random from the replay buffer o…
Deployment of emerging technologies and rapid change in industries has created a lot of risk for initiating the new projects. Many techniques and suggestions have been introduced but still lack the gap from various prospective. This paper proposes a reliable project scheduling approach. The objectives of project schedu…
Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer. Hindsight experience replay (HER) was recently proposed to tackle…
Paper improves online time series forecasting by combining natural gradient and robust t-distribution.
Digital currencies and cryptocurrencies have hesitantly started to penetrate the investors, and the next step will be the regulatory risk management framework. We examine the Value-at-Risk and Expected Shortfall properties for the major digital currencies, Bitcoin, Ethereum, Litecoin, and Ripple. The methodology used i…
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as …
Efficiently preserves old class knowledge in memory-limited settings.