- Rating
- 2(+1)
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper studies task-oriented learning and control of unknown linear dynamical systems with signal-dependent observation noise and limited communication. The proposed physical cancellation approach uses control inputs to produce small residual states with reduced absolute measurement noise, enabling iterative refinement of task-relevant estimates. Theoretical results cover controllable and underactuated systems, adaptive communication, and noise floors. Validation includes simulations on held-out linear systems supporting the predicted error rates, an analytical example demonstrating an advantage over nonadaptive acquisition, and numerical studies examining dimensional scaling, conditioning, and sensitivity to measurement and process noise.
Critical strengths
The idea of using control actions to reduce subsequent measurement noise through physical cancellation is potentially interesting.
Critical weaknesses
-
Restrictive assumptions and questionable practical significance: The main theoretical improvements rely heavily on a specialized observation model in which measurement noise decreases as the system state approaches zero. The strongest gains require vanishing noise floors and are established for relatively narrow control objectives. The paper provides insufficient justification for the practical relevance of these assumptions. Moreover, the numerical results show diminishing benefits with increasing dimensionality and, in some cases, substantially worse performance with additional refinement rounds when noise floors are present. This raises concerns about whether the theoretical improvements translate into meaningful advantages in realistic settings.
-
Severely inadequate problem formulation, exposition, and literature positioning: The paper is exceptionally poorly motivated and difficult to approach for readers outside a narrow control-theory audience. Neither the abstract nor the introduction clearly establishes the underlying control and system-identification problem, explains the practical setting, or provides sufficient intuition for why the proposed problem is important. Instead, the authors immediately introduce specialized terminology and concepts while assuming substantial prior familiarity with the field. The introduction contains only a single citation and makes virtually no attempt to situate the work within the extensive literature on adaptive control, active sensing, dual control, and experimental design. Although related work is briefly discussed near the end, this does not compensate for the lack of context and differentiation when introducing the contribution. As a result, it is unnecessarily difficult to understand the motivation, identify what is genuinely novel, or assess the broader significance of the results. These are fundamental shortcomings in the paper's scientific presentation and positioning, not merely stylistic concerns, particularly for a broad machine learning venue such as ICLR.
Questions for authors
-
Novelty and related work: How does the proposed physical cancellation mechanism fundamentally differ from existing approaches in adaptive experimental design, active sensing, and dual control? Can the authors identify the precise conceptual and technical distinctions from these established research directions and provide a more comprehensive discussion of the relevant literature?
-
Motivation and sensing assumptions: What concrete applications motivate the particular signal-dependent observation model considered in the paper? Can the authors provide realistic examples of sensing systems in which measurement noise decreases sufficiently near zero for the proposed refinement mechanism to provide meaningful benefits?
-
Practical relevance and robustness: Given that the numerical results show diminishing improvements with dimensionality and potentially severe degradation under nonzero noise floors, under what realistic operating conditions would the proposed method be preferable to standard estimation and control approaches? Can the authors characterize these conditions more explicitly?
-
Comparison with existing approaches: Could the authors provide more direct empirical comparisons against established adaptive system-identification and control methods under matched measurement, communication, and energy budgets? The current numerical evidence makes it difficult to assess the practical value of the proposed method relative to existing techniques.
-
Generality of the task formulation: To what extent can the precision improvements extend beyond minimum-energy zeroing from a fixed initial state? Given the limitations already identified for different initial preparations and other control objectives, what broader classes of practically relevant tasks could benefit from this approach?
2 comments
Response to rebuttal
I appreciate the authors' efforts to address my concerns. The revised manuscript provides substantially better motivation, literature positioning, and exposition. I am therefore raising my score from 1 to 2.
However, I find the extent of the revision somewhat difficult to evaluate, as the manuscript has undergone substantial changes beyond clarifying the original submission, including significant new experimental evidence and a reframing of the contribution. The revised paper feels considerably different from the original submission, making it challenging to assess the new claims within the scope of my initial review. I would defer to the AC and reviewers with stronger domain expertise regarding the technical significance of these additions.
Your review separates two problems, and we agree with both. The second went beyond style: the submission used its problem before stating it and placed it in the literature only at the end. The revision addresses both. For practical significance we added three kinds of evidence:
§6 (p. 9) states when the method is the right tool and when it is not.
W2/Q1. The abstract and introduction now set up the problem first, and a scalar example shows the mechanism (p. 2). The introduction now cites 21 works instead of one. The contrast with adaptive control, active sensing and dual control is in §4.3, §7 and App. O (p. 41). The main text is full, so a short version will move into the introduction for the final version.
Fisher-information designs favor large excitation, which does not help when the error grows with the signal. A correctly specified heteroscedastic design (NASD) instead rediscovers cancellation in 91% of its rounds. Active perception moves toward precise sensing but assumes known dynamics. In dual control's trade-off, each probe drives the state far from zero, but the next input brings it back, so one policy attains the optimal orders for both regulating and learning (Theorem 1), at a constant cumulative cost. What is new is the learning-theoretic account. Lower bounds match the exponents for every K-round policy, including data-dependent round times. For n≥2 and norm-proportional errors, no policy identifies the physical matrices beyond order σ, and Proposition 2 says which tasks inherit σK+1. The algorithm needs no noise model. For ICLR, this is active learning under an adaptivity budget, as in batched bandits, with minimax lower bounds.
Q2. Table 25 (p. 41) places the sensor classes of §1 on our operating map. Predicted gains are large for bfloat16 and binary16 telemetry, logarithmic quantizers and gravimetric pH dosing, borderline for FP8, and under 3× where actuation is not much more precise than sensing (piston-burette dosing 2.3×, relative navigation 0.8×). These predictions assume no floor. The pH rig, which has a measured floor, gains 75×.
W1/Q3. On the rig our recipe misses neutrality by 0.079 µM, 2.0× / 4.1× less than NASD with the measured / estimated noise law (Table 3, p. 9). The margin over the best alternative is modest, and others win where they apply. Feedback dosing with the electrode in the batch reaches 0.018 µM, a trim helps if the batch can wait 5 min, and batch-to-batch ILC matches our single batch after 3. In simulation, ILC with K+1 preparations wins 53 of 54 plant classes. The method is preferable when:
Floors and dimension. With a floor the rate saturates at σd+τ, and the gain falls roughly like 1/d. Extra rounds hurt for one reason: when the command is reconstructed through inverse powers of a contracting plant, these amplify the floor-limited error. The floor-aware rule (§4.2) fixes this. On contracting plants at d=10−3 the miss stays at 8.2×10−4 instead of growing to 3.0×10−1 by K=5 (Figure 3(a), p. 8). The gain shrinks with dimension. More rounds recover much of it on near-orthogonal plants (3.3×103× at n=8, 62× at n=16, with K=7) but not on generic plants beyond n=8, so we recommend the method for low dimension.
Q4. Table 2 and Figure 2 (p. 7) compare eight baselines with the same horizon, energy cap, readings and number K of adaptive rounds, which replaces the communication budget (App. L, p. 28). Every non-cancelling baseline stays at order σ, the best missing 1.5×104× more than ours at σ=1.3×10−3. On a contracting panel ILC with resets is best.
Q5. By Proposition 2 (p. 4), Lipschitz functions of the task coordinates (B−1AB,B−1x0) inherit σK+1. These include zeroing at every horizon, scaled targets cx0, input-energy costs and maneuvers specified through the inputs and x0. The physical matrices and maneuvers from other starts stay at order σ (App. I, p. 26).
Theorem 1 now states its quantifiers (p. 4), and §6 says what the bounds do not give. We would be grateful if you reconsidered your assessment in light of the new evidence and the scope stated in §6.