Pith. sign in

REVIEW 5 cited by

Gradients are Not All You Need

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2111.05803 v2 pith:77IZAOLO submitted 2021-11-10 cs.LG stat.ML

classification cs.LGstat.ML
keywords failuredifferentiablealgorithmsappearschaoscircumstancescommoncommunity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Differentiable programming techniques are widely used in the community and are responsible for the machine learning renaissance of the past several decades. While these methods are powerful, they have limits. In this short report, we discuss a common chaos based failure mode which appears in a variety of differentiable circumstances, ranging from recurrent neural networks and numerical physics simulation to training learned optimizers. We trace this failure to the spectrum of the Jacobian of the system under study, and provide criteria for when a practitioner might expect this failure to spoil their differentiation based optimization algorithms.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Open-DiffLoco: Open-Source Differentiable Learning for Deployable Blind Quadruped Locomotion

    cs.RO 2026-08 conditional novelty 6.0 of 10

    Differentiable simulation with SHAC and a simplified reward set trains deployable blind quadruped policies that transfer to a real Unitree Go2, plus a new critic-Jacobian supervision method (JAVE).

  2. Efficient Domain-Adaptive Policy Learning via Kernel Representation with Application to Quadrotor Control under Non-Stationary Disturbances

    cs.RO 2026-06 conditional novelty 6.0 of 10

    A quadrotor policy trained in 50 seconds of differentiable simulation adapts online by updating both random-Fourier-feature coefficients and bandwidth, improving tracking over DATT/MPC baselines in simulation and on C...

  3. RoboSSM: Scalable In-context Imitation Learning via State-Space Models

    cs.RO 2025-09 conditional novelty 6.0 of 10

    RoboSSM shows that a state-space model backbone can extend in-context imitation learning to prompts much longer than those seen in training, where a Transformer-based baseline degrades.

  4. How Should We Meta-Learn Reinforcement Learning Algorithms?

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A systematic comparison of black-box evolution, neural and symbolic distillation, and LLM-based proposal for meta-learning RL algorithms yields practical recommendations: warm-started LLM proposal is sample-efficient,...

  5. First Order Model-Based RL through Decoupled Backpropagation

    cs.RO 2025-08 conditional novelty 5.0 of 10

    By computing gradients through a learned dynamics model while unrolling trajectories in the real simulator, DMO achieves SHAC-level sample efficiency with standard simulators and deploys on a real quadruped.

Pith tools