Pith. sign in

REVIEW 16 cited by

HiPPO: Recurrent Memory with Optimal Polynomial Projections

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 2008.07669 v2 pith:E2SG64YG submitted 2020-08-17 cs.LG stat.ML

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

A central problem in learning from sequential data is representing cumulative history in an incremental fashion as more data is processed. We introduce a general framework (HiPPO) for the online compression of continuous signals and discrete time series by projection onto polynomial bases. Given a measure that specifies the importance of each time step in the past, HiPPO produces an optimal solution to a natural online function approximation problem. As special cases, our framework yields a short derivation of the recent Legendre Memory Unit (LMU) from first principles, and generalizes the ubiquitous gating mechanism of recurrent neural networks such as GRUs. This formal framework yields a new memory update mechanism (HiPPO-LegS) that scales through time to remember all history, avoiding priors on the timescale. HiPPO-LegS enjoys the theoretical benefits of timescale robustness, fast updates, and bounded gradients. By incorporating the memory dynamics into recurrent neural networks, HiPPO RNNs can empirically capture complex temporal dependencies. On the benchmark permuted MNIST dataset, HiPPO-LegS sets a new state-of-the-art accuracy of 98.3%. Finally, on a novel trajectory classification task testing robustness to out-of-distribution timescales and missing data, HiPPO-LegS outperforms RNN and neural ODE baselines by 25-40% accuracy.

Discussion (0). Sign in to comment.

Forward citations

Cited by 16 Pith papers

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

  1. Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo

    cond-mat.str-el 2026-05 conditional novelty 7.0 of 10

    PSR-NQS makes recurrent neural quantum states scalable for variational Monte Carlo by using parallel scan recurrence, reaching accurate results on 52x52 two-dimensional lattices.

  2. Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics

    cs.LG 2025-12 unverdicted novelty 7.0 of 10

    Exact Flow Linear Attention derives a closed-form exact update for delta-rule linear attention from continuous-time dynamics, removing Euler discretization error while preserving linear complexity and structure.

  3. Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation

    cs.LG 2025-09 unverdicted novelty 7.0 of 10

    Robust Filter Attention models self-attention as consistency-based state estimation under a linear SDE for token trajectories, matching standard attention complexity while showing lower perplexity and better zero-shot...

  4. L2RU: a Structured State Space Model with prescribed L2-bound

    eess.SY 2025-03 unverdicted novelty 7.0 of 10

    L2RU parametrizes SSMs to enforce a prescribed L2-gain bound for guaranteed input-output stability and robustness in all parameter regimes.

  5. Free Parametrization of L_2-Bounded Structured State-Space Controllers for Nonlinear Control with Stability Guarantees

    eess.SY 2026-06 unverdicted novelty 6.0 of 10

    A new free parametrization of L2-bounded LTI systems creates L2RU SSM layers that enforce stability by design, allowing unconstrained nonlinear controller optimization with guarantees via small-gain theorem.

  6. Beyond Similarity: Temporal Operator Attention for Time Series Analysis

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    TOA augments attention with learnable sequence-space operators and stochastic regularization to enable signed temporal mixing, yielding gains on forecasting and related benchmarks when added to PatchTST and iTransformer.

  7. Attention to Mamba: A Recipe for Cross-Architecture Distillation

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    A two-stage distillation recipe converts a Pythia-1B Transformer into a Mamba model that preserves performance with perplexity 14.11 versus the teacher's 13.86.

  8. Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation

    cs.LG 2025-09 reject novelty 6.0 of 10

    AFA re-derives self-attention as a precision-weighted robust state estimator for a linear SDE, recovering rotary encodings in a limit, but the abstract's language-modeling results are absent from the text.

  9. SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks

    cs.NE 2025-06 unverdicted novelty 6.0 of 10

    SiLIF models apply SSM dynamics and parametrization to spiking neurons for stable training, reaching new SOTA on event-based and raw-audio speech datasets while using half the compute of SSMs via synaptic delays.

  10. SketchMamba: A Lightweight State-Space Model for Joint Progressive Sketch Classification and Stroke Auto-Completion

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Dense per-step class loss on a 1.55M-parameter causal Mamba unifies progressive sketch recognition (94.93% final Top-1, 0.706 progressive AUC) and stroke auto-completion on 58-class Quick, Draw!.

  11. Q-Delta: Beyond Key-Value Associative State Evolution

    cs.AI 2026-06 unverdicted novelty 5.0 of 10

    Q-Delta extends linear attention by introducing a query-conditioned delta rule that incorporates mixed key-query errors into recurrent state updates for improved stability and performance.

  12. Beyond Similarity: Temporal Operator Attention for Time Series Analysis

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Temporal Operator Attention augments softmax attention with learnable sequence-space operators for signed temporal mixing and uses stochastic regularization to enable practical training, yielding consistent gains on t...

  13. Beyond the Autoregressive Horizon: A Comprehensive Survey of Diffusion Models, World Modelling, and State Space Models for Code

    cs.SE 2026-04 accept novelty 5.0 of 10

    A survey of diffusion, world-model, and state-space architectures for code that frames them as routes past autoregressive bottlenecks toward System-2 coding agents.

  14. Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling

    cs.LG 2025-12 conditional novelty 5.0 of 10

    The authors derive discrete-time SSMs from a lag-operator inner product and show that a Legendre/exponential-warp instance reduces to HiPPO-LegS.

  15. Rivaling Transformers: Multi-Scale Structured State-Space Mixtures for Agentic 6G O-RAN

    cs.NI 2025-10 conditional novelty 5.0 of 10

    A 0.70M-parameter multi-scale state-space mixture predicts next-step RSRP on an O-RAN testbed with RMSE 0.29 dB and R2=0.993, running 3-10x faster than the tested Transformers.

  16. Elucidating the Design Space of Decay in Linear Attention

    cs.CL 2025-09 conditional novelty 5.0 of 10

    A controlled study of decay in linear attention finds median decay near 0.8 works best, vector decay generally beats scalar decay, and RoPE/TPE give little benefit for models with sub-unity decay.

Pith tools