arXiv research

PETRA enables parallel training of deep models with reversible architectures.

Recently, deep residual networks have been successfully applied in many computer vision and natural language processing tasks, pushing the state-of-the-art performance with deeper and wider architectures. In this work, we interpret deep residual networks as ordinary differential equations (ODEs), which have long been s…

New neural net learns time-reversible symplectic dynamics.

New ODE solvers improve training efficiency and accuracy.

SARD improves deep learning clinical prediction performance.

Tuning hyperparameters of learning algorithms is hard because gradients are usually unavailable. We compute exact gradients of cross-validation performance with respect to all hyperparameters by chaining derivatives backwards through the entire training procedure. These gradients allow us to optimize thousands of hyper…

Recurrent neural networks (RNNs) are a widely used tool for modeling sequential data, yet they are often treated as inscrutable black boxes. Given a trained recurrent network, we would like to reverse engineer it--to obtain a quantitative, interpretable description of how it solves a particular task. Even for simple ta…

Deep learning has seen tremendous success over the past decade in computer vision, machine translation, and gameplay. This success rests in crucial ways on gradient-descent optimization and the ability to learn parameters of a neural network by backpropagating observed errors. However, neural network architectures are …

Intelligent Momentum Transformer outperforms traditional trading strategies.

No methods currently exist for making arbitrary neural networks fair. In this work we introduce GRAD, a new and simplified method to producing fair neural networks that can be used for auto-encoding fair representations or directly with predictive networks. It is easy to implement and add to existing architectures, has…

This paper studies deep learning methodologies for portfolio optimization in the US equities market. We present a novel residual switching network that can automatically sense changes in market regimes and switch between momentum and reversal predictors accordingly. The residual switching network architecture combines …

End-to-end policy learning improves statistical arbitrage trading.

DFM simplifies CNF training without interpolants.

A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap computation of Jacobian determinants. Alternatively, the Jacobian trace can be u…

Classifies reversible and strongly reversible elements in quaternionic groups.

The paper classifies reversible and strongly reversible elements in Hermitian isometry groups.

This paper classifies reversible and strongly reversible elements in affine groups.

Deep Learning algorithms have recently become the de-facto paradigm for various prediction problems, which include many privacy-preserving applications like online medical image analysis. Presumably, the privacy of data in a deep learning system is a serious concern. There have been several efforts to analyze and explo…

A new trading strategy using reinforcement learning for statistical arbitrage.

Algebraic method reveals criterion for quaternionic Möbius group reversibility.

Recent studies have shown that online portfolio selection strategies that exploit the mean reversion property can achieve excess return from equity markets. This paper empirically investigates the performance of state-of-the-art mean reversion strategies on real market data. The aims of the study are twofold. The first…

We address the problem of reverse engineering of stripped executables, which contain no debug information. This is a challenging problem because of the low amount of syntactic information available in stripped executables, and the diverse assembly code patterns arising from compiler optimizations. We present a novel ap…

A Finsler space is said to be geodesically reversible if each oriented geodesic can be reparametrized as a geodesic with the reverse orientation. A reversible Finsler space is geodesically reversible, but the converse need not be true. In this note, building on recent work of LeBrun and Mason, it is shown that a geodes…

We introduce graph normalizing flows: a new, reversible graph neural network model for prediction and generation. On supervised tasks, graph normalizing flows perform similarly to message passing neural networks, but at a significantly reduced memory footprint, allowing them to scale to larger graphs. In the unsupervis…

Sharp stability results for reverse isoperimetric inequalities in 2D.

Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit particular tasks. In this paper, we review several possibilites to reverse map these architectures to biologically more realistic spiking networks…

Let $G$ be a group. An element $g$ in $G$ is called reversible if it is conjugate to $g^{-1}$ within $G$, and called strongly reversible if it is conjugate to its inverse by an order two element of $G$. Let $\textbf{H}_{\mathbb H}^n$ be the $n$-dimensional quaternionic hyperbolic space. Let $\mathrm{PSp}(n,1)$ be the i…

Boundary rigidity proven for non-reversible Finsler metrics.

On-line portfolio selection has attracted increasing interests in machine learning and AI communities recently. Empirical evidences show that stock's high and low prices are temporary and stock price relatives are likely to follow the mean reversion phenomenon. While the existing mean reversion strategies are shown to …

Conditional diffusion models can approximate target distributions well with Gaussian-mixture reverse kernels.

New knots not rationally concordant to their reverses found.

The paper classifies reversible elements in Seifert-fibered spaces and braid groups.

DeepPeep attacks DNN architectures to reveal design details, posing IP theft risks.

Reverse annealing boosts quantum matrix factorization performance.

New findings show score matching's accuracy doesn't ensure numerical stability in diffusion sampling.

TRS-ODENs learn dynamics with time-reversal symmetry for more efficient learning.

Paper proves rigidity theorems for geodesically reversible Finsler metrics.

Reduces identity testing of reversible Markov chains to simpler symmetric chain tests.

Proof of reverse isoperimetric inequality for black holes.

Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data, several graph auto-encoders have recently been proposed, but they neglect to reco…

Study neural architectures on learned latent graphs using Schrödinger dynamics.

Causal deep learning tackles causal inference using tensor factor analysis.

New algorithm learns bridged diffusion processes without time-reversals.

The study characterizes diffusion model generalization using data-dependent ridge manifolds.

Model projection transfers convolutional network properties to feedforward networks.

Consider the problem of pricing options on forwards in energy markets, when spot prices follow a geometric multi-factor model in which several rates of mean reversion appear. In this paper we investigate the role played by slow mean reversion when pricing and hedging options. In particular, we determine both upper and …

Most existing approaches to clustering gene expression time course data treat the different time points as independent dimensions and are invariant to permutations, such as reversal, of the experimental time course. Approaches utilizing HMMs have been shown to be helpful in this regard, but are hampered by having to ch…

Characterizes isometries between non-reversible Finsler manifolds.