Time-Reversal Symmetric ODE Network
Time-reversal symmetry, which requires that the dynamics of a system should not change with the reversal of time axis, is a fundamental property that frequently holds in classical and quantum mechanics. In this paper, we propose a novel loss function that measures how well our ordinary differential equation (ODE) networks comply with this time-reversal symmetry; it is formally defined by the discrepancy in the time evolutions of ODE networks between forward and backward dynamics. Then, we design a new framework, which we name as Time-Reversal Symmetric ODE Networks (TRS-ODENs), that can learn the dynamics of physical systems more sample-efficiently by learning with the proposed loss function. We evaluate TRS-ODENs on several classical dynamics, and find they can learn the desired time evolution from observed noisy and complex trajectories. We also show that, even for systems that do not possess the full time-reversal symmetry, TRS-ODENs can achieve better predictive performances over baselines.
Code (1)
Similar Papers 제목 키워드 기반
Genomic and pathological analyses of an asymmetric true hermaphroditism case in a female labrador retriever
The two main gonadal development disorders in dogs are true hermaphroditism and XX male syndrome. True hermaphroditism can be divided into two subcategories: XX sex reversal and XY sex reversal. XX Sry-negative sex rever…
Reversal Invariance in Autoregressive Language Models
We formalize a structural property of the causal (autoregressive) language modeling (CLM) objective: reversal invariance. Formally, the next-token prediction loss assigns identical likelihood to a corpus and its reversal…
Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning
Symmetry is pervasive in robotics and has been widely exploited to improve sample efficiency in deep reinforcement learning (DRL). However, existing approaches primarily focus on spatial symmetries, such as reflection, r…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningComparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty
Non-stationary environments require agents to revise previously learned action values when contingencies change. We treat large language models (LLMs) as sequential decision policies in a two-option probabilistic reversa…
DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models
The "reversal curse" refers to the phenomenon where large language models (LLMs) exhibit predominantly unidirectional behavior when processing logically bidirectional relationships. Prior work attributed this to autoregr…