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
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.
Forward citations
Cited by 16 Pith papers
-
Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo
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.
-
Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics
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.
-
Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation
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...
-
L2RU: a Structured State Space Model with prescribed L2-bound
L2RU parametrizes SSMs to enforce a prescribed L2-gain bound for guaranteed input-output stability and robustness in all parameter regimes.
-
Free Parametrization of L_2-Bounded Structured State-Space Controllers for Nonlinear Control with Stability Guarantees
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.
-
Beyond Similarity: Temporal Operator Attention for Time Series Analysis
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.
-
Attention to Mamba: A Recipe for Cross-Architecture Distillation
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.
-
Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation
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.
-
SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
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.
-
SketchMamba: A Lightweight State-Space Model for Joint Progressive Sketch Classification and Stroke Auto-Completion
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!.
-
Q-Delta: Beyond Key-Value Associative State Evolution
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.
-
Beyond Similarity: Temporal Operator Attention for Time Series Analysis
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...
-
Beyond the Autoregressive Horizon: A Comprehensive Survey of Diffusion Models, World Modelling, and State Space Models for Code
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.
-
Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling
The authors derive discrete-time SSMs from a lag-operator inner product and show that a Legendre/exponential-warp instance reduces to HiPPO-LegS.
-
Rivaling Transformers: Multi-Scale Structured State-Space Mixtures for Agentic 6G O-RAN
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.
-
Elucidating the Design Space of Decay in Linear Attention
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.
Discussion (0). Sign in to comment.